Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2272 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5937. Min Act: -0.1700

Data Index: 1085963 (Open Web Text)

Max Activating Token Index: 375

Text #1

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5569. Min Act: -0.1700

Data Index: 1069941 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5653. Min Act: -0.1700

Data Index: 8155751 (Open Web Text)

Max Activating Token Index: 402

Text #3

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5680. Min Act: -0.1700

Data Index: 4779010 (Open Web Text)

Max Activating Token Index: 230

Text #4

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5884. Min Act: -0.1700

Data Index: 2248811 (Open Web Text)

Max Activating Token Index: 829

Text #5

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.6233. Min Act: -0.1700

Data Index: 2980356 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5237. Min Act: -0.1700

Data Index: 5022052 (Open Web Text)

Max Activating Token Index: 796

Text #7

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5238. Min Act: -0.1700

Data Index: 3324386 (Open Web Text)

Max Activating Token Index: 887

Text #8

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5275. Min Act: -0.1700

Data Index: 4191195 (Open Web Text)

Max Activating Token Index: 911

Text #9

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5335. Min Act: -0.1700

Data Index: 2413575 (Open Web Text)

Max Activating Token Index: 719

Text #10

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.4811. Min Act: -0.1700

Data Index: 2585670 (Open Web Text)

Max Activating Token Index: 855

Text #11

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.4964. Min Act: -0.1700

Data Index: 6857523 (Open Web Text)

Max Activating Token Index: 928

Text #12

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5345. Min Act: -0.1700

Data Index: 7890740 (Open Web Text)

Max Activating Token Index: 398

Text #13

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.4962. Min Act: -0.1700

Data Index: 8140172 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.5385. Min Act: -0.1700

Data Index: 6357981 (Open Web Text)

Max Activating Token Index: 871

Text #15

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.4805. Min Act: -0.1700

Data Index: 2006608 (Open Web Text)

Max Activating Token Index: 952

Text #16

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.4709. Min Act: -0.1700

Data Index: 5518545 (Open Web Text)

Max Activating Token Index: 320

Text #17

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.4968. Min Act: -0.1700

Data Index: 3856919 (Open Web Text)

Max Activating Token Index: 361

Text #18

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.4790. Min Act: -0.1700

Data Index: 3205129 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.4791. Min Act: -0.1700

Data Index: 5637187 (Open Web Text)

Max Activating Token Index: 252