Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6231 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.8398. Min Act: -0.1700

Data Index: 1008763 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7148. Min Act: -0.1700

Data Index: 6183662 (Open Web Text)

Max Activating Token Index: 498

Text #2

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.7148. Min Act: -0.1700

Data Index: 4637742 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.5898. Min Act: -0.1700

Data Index: 8581987 (Open Web Text)

Max Activating Token Index: 363

Text #4

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.5585. Min Act: -0.1700

Data Index: 6033412 (Open Web Text)

Max Activating Token Index: 95

Text #5

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.5273. Min Act: -0.1700

Data Index: 6290012 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.5273. Min Act: -0.1700

Data Index: 5538888 (Open Web Text)

Max Activating Token Index: 365

Text #7

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.5273. Min Act: -0.1700

Data Index: 1318126 (Open Web Text)

Max Activating Token Index: 541

Text #8

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4023. Min Act: -0.1700

Data Index: 1942146 (Open Web Text)

Max Activating Token Index: 291

Text #9

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4648. Min Act: -0.1700

Data Index: 3414325 (Open Web Text)

Max Activating Token Index: 830

Text #10

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4023. Min Act: -0.1700

Data Index: 3827787 (Open Web Text)

Max Activating Token Index: 468

Text #11

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4335. Min Act: -0.1700

Data Index: 1222312 (Open Web Text)

Max Activating Token Index: 150

Text #12

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4023. Min Act: -0.1700

Data Index: 3812798 (Open Web Text)

Max Activating Token Index: 389

Text #13

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4023. Min Act: -0.1700

Data Index: 3787783 (Open Web Text)

Max Activating Token Index: 982

Text #14

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4023. Min Act: -0.1700

Data Index: 3959775 (Open Web Text)

Max Activating Token Index: 342

Text #15

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.3710. Min Act: -0.1700

Data Index: 6821207 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.3710. Min Act: -0.1700

Data Index: 4404150 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.3085. Min Act: -0.1700

Data Index: 7481629 (Open Web Text)

Max Activating Token Index: 119

Text #18

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.3085. Min Act: -0.1700

Data Index: 3404490 (Open Web Text)

Max Activating Token Index: 249

Text #19

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2773. Min Act: -0.1700

Data Index: 4990390 (Open Web Text)

Max Activating Token Index: 875