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

Dataset: Open Web Text

Neuron 1750 in Layer 5

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: 3.1862. Min Range: -3.1862

Max Act: 3.1862. Min Act: -0.1700

Data Index: 5165918 (Open Web Text)

Max Activating Token Index: 606

Text #1

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1656. Min Act: -0.1700

Data Index: 1593868 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1415. Min Act: -0.1700

Data Index: 1603501 (Open Web Text)

Max Activating Token Index: 661

Text #3

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1468. Min Act: -0.1700

Data Index: 143389 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1366. Min Act: -0.1700

Data Index: 8557100 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1255. Min Act: -0.1700

Data Index: 5926603 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1286. Min Act: -0.1700

Data Index: 367765 (Open Web Text)

Max Activating Token Index: 817

Text #7

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1317. Min Act: -0.1700

Data Index: 8388540 (Open Web Text)

Max Activating Token Index: 437

Text #8

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1477. Min Act: -0.1700

Data Index: 6819870 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1204. Min Act: -0.1700

Data Index: 4821634 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1302. Min Act: -0.1700

Data Index: 3577174 (Open Web Text)

Max Activating Token Index: 548

Text #11

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1310. Min Act: -0.1700

Data Index: 3545530 (Open Web Text)

Max Activating Token Index: 78

Text #12

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1291. Min Act: -0.1700

Data Index: 1035765 (Open Web Text)

Max Activating Token Index: 503

Text #13

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1102. Min Act: -0.1700

Data Index: 22206 (Open Web Text)

Max Activating Token Index: 83

Text #14

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1144. Min Act: -0.1700

Data Index: 1813160 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1216. Min Act: -0.1700

Data Index: 955650 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1153. Min Act: -0.1700

Data Index: 1696551 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.0854. Min Act: -0.1700

Data Index: 2368929 (Open Web Text)

Max Activating Token Index: 341

Text #18

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.1072. Min Act: -0.1700

Data Index: 191031 (Open Web Text)

Max Activating Token Index: 472

Text #19

Max Range: 3.1862. Min Range: -3.1862

Max Act: 3.0986. Min Act: -0.1700

Data Index: 5362700 (Open Web Text)

Max Activating Token Index: 537