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

Dataset: Open Web Text

Neuron 938 in Layer 2

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: 1.8812. Min Range: -1.8812

Max Act: 1.8812. Min Act: -0.1699

Data Index: 8790369 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.8621. Min Act: -0.1700

Data Index: 953008 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.8513. Min Act: -0.1700

Data Index: 7510272 (Open Web Text)

Max Activating Token Index: 115

Text #3

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.8362. Min Act: -0.1700

Data Index: 1659155 (Open Web Text)

Max Activating Token Index: 676

Text #4

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.8170. Min Act: -0.1700

Data Index: 1908405 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.8178. Min Act: -0.1700

Data Index: 7195188 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.8031. Min Act: -0.1700

Data Index: 5575769 (Open Web Text)

Max Activating Token Index: 880

Text #7

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.8091. Min Act: -0.1700

Data Index: 5398564 (Open Web Text)

Max Activating Token Index: 892

Text #8

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7896. Min Act: -0.1700

Data Index: 1411320 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7756. Min Act: -0.1700

Data Index: 519002 (Open Web Text)

Max Activating Token Index: 449

Text #10

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7860. Min Act: -0.1700

Data Index: 8595855 (Open Web Text)

Max Activating Token Index: 351

Text #11

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7744. Min Act: -0.1700

Data Index: 4948707 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7918. Min Act: -0.1700

Data Index: 6868 (Open Web Text)

Max Activating Token Index: 840

Text #13

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7719. Min Act: -0.1700

Data Index: 1465171 (Open Web Text)

Max Activating Token Index: 86

Text #14

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7624. Min Act: -0.1700

Data Index: 7516277 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7574. Min Act: -0.1700

Data Index: 2910341 (Open Web Text)

Max Activating Token Index: 717

Text #16

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7430. Min Act: -0.1700

Data Index: 2238341 (Open Web Text)

Max Activating Token Index: 845

Text #17

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7474. Min Act: -0.1700

Data Index: 1309390 (Open Web Text)

Max Activating Token Index: 651

Text #18

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7262. Min Act: -0.1700

Data Index: 7324073 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7336. Min Act: -0.1700

Data Index: 8576155 (Open Web Text)

Max Activating Token Index: 175