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

Dataset: Open Web Text

Neuron 2309 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: 3.8154. Min Range: -3.8154

Max Act: 3.8154. Min Act: -0.1700

Data Index: 4557357 (Open Web Text)

Max Activating Token Index: 709

Text #1

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.7572. Min Act: -0.1700

Data Index: 8108626 (Open Web Text)

Max Activating Token Index: 660

Text #2

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.7475. Min Act: -0.1700

Data Index: 2951963 (Open Web Text)

Max Activating Token Index: 381

Text #3

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.7433. Min Act: -0.1700

Data Index: 3015850 (Open Web Text)

Max Activating Token Index: 521

Text #4

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.6634. Min Act: -0.1700

Data Index: 5284711 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.6554. Min Act: -0.1700

Data Index: 8071035 (Open Web Text)

Max Activating Token Index: 806

Text #6

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.6301. Min Act: -0.1700

Data Index: 1449419 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.6374. Min Act: -0.1700

Data Index: 2736522 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.6281. Min Act: -0.1700

Data Index: 4347012 (Open Web Text)

Max Activating Token Index: 584

Text #9

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.6323. Min Act: -0.1700

Data Index: 2342662 (Open Web Text)

Max Activating Token Index: 219

Text #10

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.6399. Min Act: -0.1700

Data Index: 92761 (Open Web Text)

Max Activating Token Index: 473

Text #11

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.6140. Min Act: -0.1700

Data Index: 8075473 (Open Web Text)

Max Activating Token Index: 65

Text #12

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.6006. Min Act: -0.1700

Data Index: 7151326 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.5870. Min Act: -0.1700

Data Index: 259060 (Open Web Text)

Max Activating Token Index: 883

Text #14

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.5751. Min Act: -0.1700

Data Index: 2424303 (Open Web Text)

Max Activating Token Index: 672

Text #15

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.5672. Min Act: -0.1700

Data Index: 6566353 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.5701. Min Act: -0.1700

Data Index: 4960438 (Open Web Text)

Max Activating Token Index: 362

Text #17

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.5629. Min Act: -0.1700

Data Index: 5154200 (Open Web Text)

Max Activating Token Index: 351

Text #18

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.5501. Min Act: -0.1700

Data Index: 3230285 (Open Web Text)

Max Activating Token Index: 584

Text #19

Max Range: 3.8154. Min Range: -3.8154

Max Act: 3.5321. Min Act: -0.1700

Data Index: 7478535 (Open Web Text)

Max Activating Token Index: 402