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

Dataset: Open Web Text

Neuron 2748 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: 3.9331. Min Range: -3.9331

Max Act: 3.9331. Min Act: -0.1700

Data Index: 1352510 (Open Web Text)

Max Activating Token Index: 343

Text #1

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.8080. Min Act: -0.1700

Data Index: 5209474 (Open Web Text)

Max Activating Token Index: 358

Text #2

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7248. Min Act: -0.1700

Data Index: 5132787 (Open Web Text)

Max Activating Token Index: 791

Text #3

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7322. Min Act: -0.1700

Data Index: 4773634 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6093. Min Act: -0.1700

Data Index: 777872 (Open Web Text)

Max Activating Token Index: 802

Text #5

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6091. Min Act: -0.1700

Data Index: 597491 (Open Web Text)

Max Activating Token Index: 678

Text #6

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6031. Min Act: -0.1700

Data Index: 2692639 (Open Web Text)

Max Activating Token Index: 465

Text #7

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5740. Min Act: -0.1700

Data Index: 3676381 (Open Web Text)

Max Activating Token Index: 865

Text #8

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5607. Min Act: -0.1700

Data Index: 921031 (Open Web Text)

Max Activating Token Index: 980

Text #9

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5713. Min Act: -0.1700

Data Index: 836827 (Open Web Text)

Max Activating Token Index: 494

Text #10

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5609. Min Act: -0.1700

Data Index: 7461479 (Open Web Text)

Max Activating Token Index: 1002

Text #11

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5841. Min Act: -0.1700

Data Index: 1116714 (Open Web Text)

Max Activating Token Index: 347

Text #12

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5905. Min Act: -0.1700

Data Index: 7462885 (Open Web Text)

Max Activating Token Index: 239

Text #13

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5221. Min Act: -0.1700

Data Index: 5623670 (Open Web Text)

Max Activating Token Index: 567

Text #14

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5029. Min Act: -0.1700

Data Index: 6534026 (Open Web Text)

Max Activating Token Index: 569

Text #15

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5446. Min Act: -0.1700

Data Index: 7767249 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5429. Min Act: -0.1700

Data Index: 5747474 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5382. Min Act: -0.1700

Data Index: 81845 (Open Web Text)

Max Activating Token Index: 283

Text #18

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5655. Min Act: -0.1700

Data Index: 2083670 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.5346. Min Act: -0.1700

Data Index: 1291454 (Open Web Text)

Max Activating Token Index: 523