Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1093 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3709. Min Act: -0.0000

Data Index: 732975 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3495. Min Act: -0.0000

Data Index: 758834 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3518. Min Act: -0.0000

Data Index: 245313 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1473934 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3415. Min Act: -0.0000

Data Index: 945228 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1745741 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3455. Min Act: -0.0000

Data Index: 137036 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1620093 (The Pile)

Max Activating Token Index: 305

Text #8

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1372474 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1117976 (The Pile)

Max Activating Token Index: 409

Text #10

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1583841 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3585. Min Act: -0.0000

Data Index: 278586 (The Pile)

Max Activating Token Index: 48

Text #12

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1860507 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1781382 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1715733 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3154. Min Act: -0.0000

Data Index: 594441 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3198. Min Act: -0.0000

Data Index: 26725 (The Pile)

Max Activating Token Index: 145

Text #17

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3211. Min Act: -0.0000

Data Index: 439535 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1392705 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1477635 (The Pile)

Max Activating Token Index: 723