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

Dataset: The Pile

Neuron 1970 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: 0.6472. Min Range: -0.6472

Max Act: 0.6472. Min Act: -0.0000

Data Index: 835313 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1688329 (The Pile)

Max Activating Token Index: 426

Text #2

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1053868 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5919. Min Act: -0.0000

Data Index: 656553 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1297956 (The Pile)

Max Activating Token Index: 315

Text #5

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1972334 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5228. Min Act: -0.0000

Data Index: 545491 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5898. Min Act: -0.0000

Data Index: 761157 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5480. Min Act: -0.0000

Data Index: 169489 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1532829 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1924673 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5033. Min Act: -0.0000

Data Index: 692760 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5361. Min Act: -0.0000

Data Index: 378520 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1034359 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5296. Min Act: -0.0000

Data Index: 625429 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1627756 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1409728 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1662967 (The Pile)

Max Activating Token Index: 149

Text #18

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1202208 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4772. Min Act: -0.0000

Data Index: 447115 (The Pile)

Max Activating Token Index: 84