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

Dataset: Open Web Text

Neuron 1178 in Layer 46

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.8398. Min Act: -0.1700

Data Index: 3905279 (Open Web Text)

Max Activating Token Index: 743

Text #1

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.6211. Min Act: -0.1700

Data Index: 985220 (Open Web Text)

Max Activating Token Index: 166

Text #2

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.5273. Min Act: -0.1700

Data Index: 1950195 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.5273. Min Act: -0.1700

Data Index: 587545 (Open Web Text)

Max Activating Token Index: 458

Text #4

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3398. Min Act: -0.1700

Data Index: 950970 (Open Web Text)

Max Activating Token Index: 110

Text #5

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3086. Min Act: -0.1700

Data Index: 7664075 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3086. Min Act: -0.1700

Data Index: 4698808 (Open Web Text)

Max Activating Token Index: 962

Text #7

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.2461. Min Act: -0.1700

Data Index: 2390486 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.2148. Min Act: -0.1700

Data Index: 1310358 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.2148. Min Act: -0.1700

Data Index: 2418985 (Open Web Text)

Max Activating Token Index: 903

Text #10

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1836. Min Act: -0.1700

Data Index: 5326047 (Open Web Text)

Max Activating Token Index: 833

Text #11

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1836. Min Act: -0.1700

Data Index: 1347572 (Open Web Text)

Max Activating Token Index: 144

Text #12

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1836. Min Act: -0.1700

Data Index: 8031655 (Open Web Text)

Max Activating Token Index: 316

Text #13

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1523. Min Act: -0.1700

Data Index: 4384775 (Open Web Text)

Max Activating Token Index: 811

Text #14

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1211. Min Act: -0.1700

Data Index: 7767298 (Open Web Text)

Max Activating Token Index: 794

Text #15

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1211. Min Act: -0.1700

Data Index: 8073238 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1211. Min Act: -0.1700

Data Index: 8211837 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1211. Min Act: -0.1700

Data Index: 7307730 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.0898. Min Act: -0.1700

Data Index: 4105934 (Open Web Text)

Max Activating Token Index: 93

Text #19

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.0586. Min Act: -0.1700

Data Index: 945298 (Open Web Text)

Max Activating Token Index: 1002