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

Dataset: Open Web Text

Neuron 412 in Layer 1

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: 3.9428. Min Range: -3.9428

Max Act: 3.9428. Min Act: -0.1700

Data Index: 1855225 (Open Web Text)

Max Activating Token Index: 378

Text #1

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.9055. Min Act: -0.1700

Data Index: 523967 (Open Web Text)

Max Activating Token Index: 576

Text #2

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8958. Min Act: -0.1700

Data Index: 1466800 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8601. Min Act: -0.1700

Data Index: 5450004 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8770. Min Act: -0.1700

Data Index: 1033335 (Open Web Text)

Max Activating Token Index: 353

Text #5

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8718. Min Act: -0.1700

Data Index: 2354049 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8274. Min Act: -0.1700

Data Index: 1185190 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8613. Min Act: -0.1700

Data Index: 1359624 (Open Web Text)

Max Activating Token Index: 495

Text #8

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8422. Min Act: -0.1700

Data Index: 3286601 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8569. Min Act: -0.1700

Data Index: 7838770 (Open Web Text)

Max Activating Token Index: 139

Text #10

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8440. Min Act: -0.1700

Data Index: 7024061 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8388. Min Act: -0.1700

Data Index: 3417604 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8405. Min Act: -0.1700

Data Index: 6860895 (Open Web Text)

Max Activating Token Index: 339

Text #13

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8518. Min Act: -0.1700

Data Index: 2195102 (Open Web Text)

Max Activating Token Index: 542

Text #14

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8270. Min Act: -0.1700

Data Index: 6550648 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8348. Min Act: -0.1700

Data Index: 1118260 (Open Web Text)

Max Activating Token Index: 689

Text #16

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8168. Min Act: -0.1700

Data Index: 392073 (Open Web Text)

Max Activating Token Index: 948

Text #17

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8200. Min Act: -0.1700

Data Index: 3367856 (Open Web Text)

Max Activating Token Index: 203

Text #18

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8224. Min Act: -0.1700

Data Index: 3394253 (Open Web Text)

Max Activating Token Index: 189

Text #19

Max Range: 3.9428. Min Range: -3.9428

Max Act: 3.8039. Min Act: -0.1700

Data Index: 3394613 (Open Web Text)

Max Activating Token Index: 107