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

Dataset: Open Web Text

Neuron 2622 in Layer 6

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: 3.8373. Min Range: -3.8373

Max Act: 3.8373. Min Act: -0.1700

Data Index: 4996953 (Open Web Text)

Max Activating Token Index: 767

Text #1

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6575. Min Act: -0.1700

Data Index: 4165383 (Open Web Text)

Max Activating Token Index: 449

Text #2

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6551. Min Act: -0.1700

Data Index: 5053072 (Open Web Text)

Max Activating Token Index: 472

Text #3

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6386. Min Act: -0.1700

Data Index: 6304592 (Open Web Text)

Max Activating Token Index: 123

Text #4

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6209. Min Act: -0.1700

Data Index: 4021940 (Open Web Text)

Max Activating Token Index: 978

Text #5

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5842. Min Act: -0.1700

Data Index: 5457307 (Open Web Text)

Max Activating Token Index: 750

Text #6

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5708. Min Act: -0.1700

Data Index: 3449490 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5193. Min Act: -0.1700

Data Index: 1538922 (Open Web Text)

Max Activating Token Index: 815

Text #8

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5468. Min Act: -0.1700

Data Index: 634409 (Open Web Text)

Max Activating Token Index: 542

Text #9

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5465. Min Act: -0.1700

Data Index: 3579294 (Open Web Text)

Max Activating Token Index: 413

Text #10

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5365. Min Act: -0.1700

Data Index: 3348469 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5285. Min Act: -0.1700

Data Index: 2554146 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5192. Min Act: -0.1700

Data Index: 7142737 (Open Web Text)

Max Activating Token Index: 677

Text #13

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5348. Min Act: -0.1700

Data Index: 6524474 (Open Web Text)

Max Activating Token Index: 582

Text #14

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5206. Min Act: -0.1700

Data Index: 5328972 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5495. Min Act: -0.1700

Data Index: 406300 (Open Web Text)

Max Activating Token Index: 338

Text #16

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.4866. Min Act: -0.1700

Data Index: 7142732 (Open Web Text)

Max Activating Token Index: 887

Text #17

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.4905. Min Act: -0.1700

Data Index: 2645117 (Open Web Text)

Max Activating Token Index: 669

Text #18

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.4823. Min Act: -0.1700

Data Index: 7253091 (Open Web Text)

Max Activating Token Index: 713

Text #19

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.4862. Min Act: -0.1700

Data Index: 8825041 (Open Web Text)

Max Activating Token Index: 635