Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1655 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8244. Min Act: -0.0000

Data Index: 101287 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1926089 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1347247 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7667. Min Act: -0.0000

Data Index: 541366 (The Pile)

Max Activating Token Index: 250

Text #4

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7597. Min Act: -0.0000

Data Index: 113124 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7779. Min Act: -0.0000

Data Index: 285557 (The Pile)

Max Activating Token Index: 418

Text #6

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7868. Min Act: -0.0000

Data Index: 332880 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1802362 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7163. Min Act: -0.0000

Data Index: 730680 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1530227 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1634975 (The Pile)

Max Activating Token Index: 351

Text #11

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1052306 (The Pile)

Max Activating Token Index: 665

Text #12

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1218903 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8317. Min Act: -0.0000

Data Index: 11292 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.5644. Min Act: -0.0000

Data Index: 144587 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1008678 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7198. Min Act: -0.0000

Data Index: 212454 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7158. Min Act: -0.0000

Data Index: 720026 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6720. Min Act: -0.0000

Data Index: 216875 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1841441 (The Pile)

Max Activating Token Index: 675