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

Dataset: Open Web Text

Neuron 830 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: 3.8315. Min Range: -3.8315

Max Act: 3.8315. Min Act: -0.1700

Data Index: 4868369 (Open Web Text)

Max Activating Token Index: 103

Text #1

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.8131. Min Act: -0.1700

Data Index: 582131 (Open Web Text)

Max Activating Token Index: 673

Text #2

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.7608. Min Act: -0.1700

Data Index: 3719256 (Open Web Text)

Max Activating Token Index: 876

Text #3

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.7062. Min Act: -0.1700

Data Index: 7291268 (Open Web Text)

Max Activating Token Index: 1006

Text #4

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.7326. Min Act: -0.1700

Data Index: 2149044 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6629. Min Act: -0.1700

Data Index: 2565235 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6810. Min Act: -0.1700

Data Index: 2495800 (Open Web Text)

Max Activating Token Index: 508

Text #7

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6550. Min Act: -0.1700

Data Index: 347672 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6298. Min Act: -0.1700

Data Index: 5355567 (Open Web Text)

Max Activating Token Index: 424

Text #9

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6192. Min Act: -0.1700

Data Index: 3743119 (Open Web Text)

Max Activating Token Index: 120

Text #10

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.5938. Min Act: -0.1700

Data Index: 4713807 (Open Web Text)

Max Activating Token Index: 564

Text #11

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6115. Min Act: -0.1700

Data Index: 1398343 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.6031. Min Act: -0.1700

Data Index: 1292072 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.5568. Min Act: -0.1700

Data Index: 7857001 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.5375. Min Act: -0.1700

Data Index: 4759984 (Open Web Text)

Max Activating Token Index: 301

Text #15

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.5512. Min Act: -0.1700

Data Index: 4931619 (Open Web Text)

Max Activating Token Index: 222

Text #16

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.5454. Min Act: -0.1700

Data Index: 5928503 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.5420. Min Act: -0.1700

Data Index: 6454400 (Open Web Text)

Max Activating Token Index: 577

Text #18

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.5338. Min Act: -0.1700

Data Index: 6764612 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 3.8315. Min Range: -3.8315

Max Act: 3.5241. Min Act: -0.1700

Data Index: 1454853 (Open Web Text)

Max Activating Token Index: 254