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

Dataset: Open Web Text

Neuron 2413 in Layer 21

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: 959213 (Open Web Text)

Max Activating Token Index: 207

Text #1

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.5898. Min Act: -0.1700

Data Index: 7100389 (Open Web Text)

Max Activating Token Index: 880

Text #2

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4961. Min Act: -0.1700

Data Index: 1437233 (Open Web Text)

Max Activating Token Index: 1012

Text #3

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4648. Min Act: -0.1700

Data Index: 1052609 (Open Web Text)

Max Activating Token Index: 769

Text #4

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4336. Min Act: -0.1700

Data Index: 1981456 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4336. Min Act: -0.1700

Data Index: 1777834 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4023. Min Act: -0.1700

Data Index: 5464945 (Open Web Text)

Max Activating Token Index: 769

Text #7

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4336. Min Act: -0.1700

Data Index: 4386493 (Open Web Text)

Max Activating Token Index: 308

Text #8

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.4336. Min Act: -0.1700

Data Index: 1897604 (Open Web Text)

Max Activating Token Index: 848

Text #9

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.3398. Min Act: -0.1700

Data Index: 959210 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.3086. Min Act: -0.1700

Data Index: 7600120 (Open Web Text)

Max Activating Token Index: 966

Text #11

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2773. Min Act: -0.1700

Data Index: 116148 (Open Web Text)

Max Activating Token Index: 951

Text #12

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2773. Min Act: -0.1700

Data Index: 1719244 (Open Web Text)

Max Activating Token Index: 47

Text #13

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2773. Min Act: -0.1700

Data Index: 8148303 (Open Web Text)

Max Activating Token Index: 289

Text #14

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2773. Min Act: -0.1700

Data Index: 2011607 (Open Web Text)

Max Activating Token Index: 359

Text #15

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2773. Min Act: -0.1700

Data Index: 3742181 (Open Web Text)

Max Activating Token Index: 356

Text #16

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2461. Min Act: -0.1700

Data Index: 6063223 (Open Web Text)

Max Activating Token Index: 966

Text #17

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2461. Min Act: -0.1700

Data Index: 2240759 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2148. Min Act: -0.1700

Data Index: 6547106 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 5.8398. Min Range: -5.8398

Max Act: 5.2461. Min Act: -0.1700

Data Index: 7276612 (Open Web Text)

Max Activating Token Index: 823