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

Dataset: The Pile

Neuron 792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1921580 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1610201 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1742853 (The Pile)

Max Activating Token Index: 926

Text #3

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1959340 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1180912 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3560. Min Act: -0.0000

Data Index: 273291 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3566. Min Act: -0.0000

Data Index: 440629 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1920741 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1238161 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1421807 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1940504 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1706935 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3292. Min Act: -0.0000

Data Index: 686428 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3096. Min Act: -0.0000

Data Index: 122058 (The Pile)

Max Activating Token Index: 946

Text #14

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3343. Min Act: -0.0000

Data Index: 638406 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1890915 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3460. Min Act: -0.0000

Data Index: 910146 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1613740 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1239265 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 0.6219. Min Range: -0.6219

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1205305 (The Pile)

Max Activating Token Index: 781