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

Dataset: The Pile

Neuron 697 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: 0.8566. Min Range: -0.8566

Max Act: 0.8566. Min Act: -0.0000

Data Index: 85510 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1751730 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1308355 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1874018 (The Pile)

Max Activating Token Index: 344

Text #4

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1733338 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6949. Min Act: -0.0000

Data Index: 891106 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1028958 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1838092 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6848. Min Act: -0.0000

Data Index: 944158 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6143. Min Act: -0.0000

Data Index: 419958 (The Pile)

Max Activating Token Index: 778

Text #10

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6644. Min Act: -0.0000

Data Index: 3045 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6474. Min Act: -0.0000

Data Index: 19006 (The Pile)

Max Activating Token Index: 996

Text #12

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1606332 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1927570 (The Pile)

Max Activating Token Index: 802

Text #14

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1304556 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6239. Min Act: -0.0000

Data Index: 838568 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1299969 (The Pile)

Max Activating Token Index: 807

Text #17

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6149. Min Act: -0.0000

Data Index: 278557 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6040. Min Act: -0.0000

Data Index: 360711 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.5919. Min Act: -0.0000

Data Index: 806239 (The Pile)

Max Activating Token Index: 279