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

Dataset: Open Web Text

Neuron 74 in Layer 4

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: 4.3294. Min Range: -4.3294

Max Act: 4.3294. Min Act: -0.1700

Data Index: 2767386 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.1182. Min Act: -0.1700

Data Index: 6772535 (Open Web Text)

Max Activating Token Index: 602

Text #2

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0980. Min Act: -0.1700

Data Index: 7057601 (Open Web Text)

Max Activating Token Index: 449

Text #3

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0799. Min Act: -0.1700

Data Index: 1534590 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0201. Min Act: -0.1700

Data Index: 7192155 (Open Web Text)

Max Activating Token Index: 640

Text #5

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0374. Min Act: -0.1700

Data Index: 1361084 (Open Web Text)

Max Activating Token Index: 800

Text #6

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0487. Min Act: -0.1700

Data Index: 279455 (Open Web Text)

Max Activating Token Index: 263

Text #7

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0760. Min Act: -0.1700

Data Index: 8107514 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0703. Min Act: -0.1700

Data Index: 986314 (Open Web Text)

Max Activating Token Index: 867

Text #9

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0631. Min Act: -0.1700

Data Index: 4132637 (Open Web Text)

Max Activating Token Index: 429

Text #10

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0308. Min Act: -0.1700

Data Index: 1226942 (Open Web Text)

Max Activating Token Index: 452

Text #11

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0285. Min Act: -0.1700

Data Index: 6354089 (Open Web Text)

Max Activating Token Index: 847

Text #12

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0334. Min Act: -0.1700

Data Index: 6113152 (Open Web Text)

Max Activating Token Index: 556

Text #13

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0491. Min Act: -0.1700

Data Index: 5728221 (Open Web Text)

Max Activating Token Index: 712

Text #14

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0252. Min Act: -0.1700

Data Index: 4740314 (Open Web Text)

Max Activating Token Index: 421

Text #15

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0188. Min Act: -0.1700

Data Index: 4383282 (Open Web Text)

Max Activating Token Index: 353

Text #16

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0508. Min Act: -0.1700

Data Index: 1708615 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0393. Min Act: -0.1700

Data Index: 1191010 (Open Web Text)

Max Activating Token Index: 136

Text #18

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0362. Min Act: -0.1700

Data Index: 715183 (Open Web Text)

Max Activating Token Index: 416

Text #19

Max Range: 4.3294. Min Range: -4.3294

Max Act: 4.0403. Min Act: -0.1700

Data Index: 1654306 (Open Web Text)

Max Activating Token Index: 354