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

Dataset: Open Web Text

Neuron 1687 in Layer 6

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: 5.2399. Min Range: -5.2399

Max Act: 5.2383. Min Act: -0.1700

Data Index: 8615663 (Open Web Text)

Max Activating Token Index: 187

Text #1

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.2399. Min Act: -0.1700

Data Index: 6316068 (Open Web Text)

Max Activating Token Index: 144

Text #2

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.2236. Min Act: -0.1700

Data Index: 2563987 (Open Web Text)

Max Activating Token Index: 924

Text #3

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1808. Min Act: -0.1700

Data Index: 5487627 (Open Web Text)

Max Activating Token Index: 988

Text #4

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1678. Min Act: -0.1700

Data Index: 6243250 (Open Web Text)

Max Activating Token Index: 233

Text #5

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1810. Min Act: -0.1700

Data Index: 179333 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1639. Min Act: -0.1700

Data Index: 917693 (Open Web Text)

Max Activating Token Index: 681

Text #7

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1788. Min Act: -0.1700

Data Index: 6835767 (Open Web Text)

Max Activating Token Index: 544

Text #8

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1587. Min Act: -0.1700

Data Index: 7868160 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1177. Min Act: -0.1700

Data Index: 8380646 (Open Web Text)

Max Activating Token Index: 361

Text #10

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1314. Min Act: -0.1700

Data Index: 6839256 (Open Web Text)

Max Activating Token Index: 480

Text #11

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1515. Min Act: -0.1700

Data Index: 237472 (Open Web Text)

Max Activating Token Index: 248

Text #12

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1002. Min Act: -0.1700

Data Index: 6681955 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1286. Min Act: -0.1700

Data Index: 6821791 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1102. Min Act: -0.1700

Data Index: 3637592 (Open Web Text)

Max Activating Token Index: 393

Text #15

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.0711. Min Act: -0.1700

Data Index: 3871272 (Open Web Text)

Max Activating Token Index: 766

Text #16

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1136. Min Act: -0.1700

Data Index: 1764824 (Open Web Text)

Max Activating Token Index: 395

Text #17

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1362. Min Act: -0.1700

Data Index: 3463845 (Open Web Text)

Max Activating Token Index: 820

Text #18

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.1189. Min Act: -0.1700

Data Index: 4392511 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 5.2399. Min Range: -5.2399

Max Act: 5.0810. Min Act: -0.1700

Data Index: 5713203 (Open Web Text)

Max Activating Token Index: 1006