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

Dataset: Open Web Text

Neuron 146 in Layer 5

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: 3.1473. Min Range: -3.1473

Max Act: 3.1473. Min Act: -0.1700

Data Index: 7220536 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.1207. Min Act: -0.1700

Data Index: 3452750 (Open Web Text)

Max Activating Token Index: 583

Text #2

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0404. Min Act: -0.1700

Data Index: 7829982 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0352. Min Act: -0.1700

Data Index: 7461729 (Open Web Text)

Max Activating Token Index: 90

Text #4

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0375. Min Act: -0.1700

Data Index: 1507463 (Open Web Text)

Max Activating Token Index: 240

Text #5

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0280. Min Act: -0.1700

Data Index: 4832927 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0184. Min Act: -0.1700

Data Index: 7651814 (Open Web Text)

Max Activating Token Index: 338

Text #7

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9810. Min Act: -0.1700

Data Index: 4975855 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9600. Min Act: -0.1700

Data Index: 461233 (Open Web Text)

Max Activating Token Index: 275

Text #9

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9484. Min Act: -0.1700

Data Index: 6795509 (Open Web Text)

Max Activating Token Index: 421

Text #10

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9560. Min Act: -0.1700

Data Index: 3110207 (Open Web Text)

Max Activating Token Index: 353

Text #11

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9414. Min Act: -0.1700

Data Index: 6125467 (Open Web Text)

Max Activating Token Index: 348

Text #12

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9436. Min Act: -0.1700

Data Index: 5008599 (Open Web Text)

Max Activating Token Index: 662

Text #13

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9237. Min Act: -0.1700

Data Index: 1942528 (Open Web Text)

Max Activating Token Index: 431

Text #14

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9333. Min Act: -0.1700

Data Index: 1115748 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9297. Min Act: -0.1700

Data Index: 1496511 (Open Web Text)

Max Activating Token Index: 667

Text #16

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9160. Min Act: -0.1700

Data Index: 6637703 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9220. Min Act: -0.1700

Data Index: 5937280 (Open Web Text)

Max Activating Token Index: 951

Text #18

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9249. Min Act: -0.1700

Data Index: 66508 (Open Web Text)

Max Activating Token Index: 387

Text #19

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9036. Min Act: -0.1700

Data Index: 363264 (Open Web Text)

Max Activating Token Index: 447