SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.02695 · EMNLP · 2020

Analyzing Individual Neurons in Pre-trained Language Models

Yonatan Belinkov, Fahim Dalvi, Nadir Durrani, Hassan Sajjad

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

While a lot of analysis has been carried to demonstrate linguistic knowledge captured by the representations learned within deep NLP models, very little attention has been paid towards individual neurons. We carry out a neuron-level analysis using core linguistic tasks of predicting morphology, syntax and semantics, on pre-trained language models, with questions like: i) do individual neurons in pretrained models capture linguistic information? ii) which parts of the network learn more about certain linguistic phenomena? iii) how distributed or focused is the information? and iv) how do various architectures differ in learning these properties? We found small subsets of neurons to predict linguistic tasks, with lower level tasks (such as morphology) localized in fewer neurons, compared to higher level task of predicting syntax. Our study reveals interesting cross architectural comparisons. For example, we found neurons in XLNet to be more localized and disjoint when predicting properties compared to BERT and others, where they are more distributed and coupled.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2010.02695")
get_code_for_paper("2010.02695")
have("2010.02695")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2010.02695.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2010.02695.svg)](https://syntology.ai/paper/2010.02695)

Connect an agent — have() is free.