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

Dataset: Open Web Text

Neuron 1057 in Layer 1

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: 3.7897. Min Range: -3.7897

Max Act: 3.7897. Min Act: -0.1700

Data Index: 7287674 (Open Web Text)

Max Activating Token Index: 198

Text #1

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.7301. Min Act: -0.1700

Data Index: 1004978 (Open Web Text)

Max Activating Token Index: 253

Text #2

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6595. Min Act: -0.1700

Data Index: 4597349 (Open Web Text)

Max Activating Token Index: 374

Text #3

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6673. Min Act: -0.1700

Data Index: 5046157 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6429. Min Act: -0.1700

Data Index: 3133054 (Open Web Text)

Max Activating Token Index: 979

Text #5

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6236. Min Act: -0.1700

Data Index: 4032138 (Open Web Text)

Max Activating Token Index: 398

Text #6

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6345. Min Act: -0.1700

Data Index: 1449513 (Open Web Text)

Max Activating Token Index: 354

Text #7

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6379. Min Act: -0.1700

Data Index: 42159 (Open Web Text)

Max Activating Token Index: 492

Text #8

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6330. Min Act: -0.1700

Data Index: 2131224 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6259. Min Act: -0.1700

Data Index: 2585317 (Open Web Text)

Max Activating Token Index: 262

Text #10

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6311. Min Act: -0.1700

Data Index: 7282879 (Open Web Text)

Max Activating Token Index: 182

Text #11

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6459. Min Act: -0.1700

Data Index: 5946450 (Open Web Text)

Max Activating Token Index: 421

Text #12

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6501. Min Act: -0.1700

Data Index: 5473809 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6318. Min Act: -0.1700

Data Index: 1896214 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.5954. Min Act: -0.1700

Data Index: 2683872 (Open Web Text)

Max Activating Token Index: 238

Text #15

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6200. Min Act: -0.1700

Data Index: 5020581 (Open Web Text)

Max Activating Token Index: 956

Text #16

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6164. Min Act: -0.1700

Data Index: 2401935 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6156. Min Act: -0.1700

Data Index: 924633 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6046. Min Act: -0.1700

Data Index: 2550577 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.5902. Min Act: -0.1700

Data Index: 576919 (Open Web Text)

Max Activating Token Index: 817