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

Dataset: Open Web Text

Neuron 726 in Layer 0

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: 3.1699. Min Range: -3.1699

Max Act: 3.1699. Min Act: -0.1700

Data Index: 7129918 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.1278. Min Act: -0.1700

Data Index: 7128998 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.1052. Min Act: -0.1700

Data Index: 8512442 (Open Web Text)

Max Activating Token Index: 942

Text #3

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0767. Min Act: -0.1700

Data Index: 314638 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0699. Min Act: -0.1700

Data Index: 4264024 (Open Web Text)

Max Activating Token Index: 898

Text #5

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0792. Min Act: -0.1700

Data Index: 6239606 (Open Web Text)

Max Activating Token Index: 911

Text #6

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0654. Min Act: -0.1700

Data Index: 6932438 (Open Web Text)

Max Activating Token Index: 807

Text #7

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0744. Min Act: -0.1700

Data Index: 2735834 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0588. Min Act: -0.1700

Data Index: 5773218 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0385. Min Act: -0.1700

Data Index: 596174 (Open Web Text)

Max Activating Token Index: 842

Text #10

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0360. Min Act: -0.1700

Data Index: 7561256 (Open Web Text)

Max Activating Token Index: 793

Text #11

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0332. Min Act: -0.1700

Data Index: 8624980 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0165. Min Act: -0.1700

Data Index: 3824167 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0148. Min Act: -0.1700

Data Index: 2132298 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0288. Min Act: -0.1700

Data Index: 7130922 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0282. Min Act: -0.1700

Data Index: 8410782 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0065. Min Act: -0.1700

Data Index: 8390499 (Open Web Text)

Max Activating Token Index: 436

Text #17

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0005. Min Act: -0.1700

Data Index: 2994309 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0180. Min Act: -0.1700

Data Index: 744626 (Open Web Text)

Max Activating Token Index: 807

Text #19

Max Range: 3.1699. Min Range: -3.1699

Max Act: 3.0122. Min Act: -0.1700

Data Index: 5388453 (Open Web Text)

Max Activating Token Index: 403