Emergent Modularity in Pre-trained Transformers

TL;DR

This paper investigates the emergence of modularity in pre-trained Transformers, demonstrating that neurons form functionally specialized experts early in training, which impacts their functions and structure.

Contribution

It provides empirical evidence of functional modularity in Transformers and analyzes how modular structures develop during pre-training.

Findings

Functional experts are present in Transformers.

Perturbing experts affects corresponding functions.

Modularity stabilizes early in training.

Abstract

This work examines the presence of modularity in pre-trained Transformers, a feature commonly found in human brains and thought to be vital for general intelligence. In analogy to human brains, we consider two main characteristics of modularity: (1) functional specialization of neurons: we evaluate whether each neuron is mainly specialized in a certain function, and find that the answer is yes. (2) function-based neuron grouping: we explore finding a structure that groups neurons into modules by function, and each module works for its corresponding function. Given the enormous amount of possible structures, we focus on Mixture-of-Experts as a promising candidate, which partitions neurons into experts and usually activates different experts for different inputs. Experimental results show that there are functional experts, where clustered are the neurons specialized in a certain function. Moreover, perturbing the activations of functional experts significantly affects the corresponding function. Finally, we study how modularity emerges during pre-training, and find that the modular structure is stabilized at the early stage, which is faster than neuron stabilization. It suggests that Transformers first construct the modular structure and then learn fine-grained neuron functions. Our code and data are available at https://github.com/THUNLP/modularity-analysis.