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

Dataset: The Pile

Neuron 3714 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1813078 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1872017 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.4693. Min Act: -0.0000

Data Index: 885547 (The Pile)

Max Activating Token Index: 695

Text #3

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1334309 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3997. Min Act: -0.0000

Data Index: 355730 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3960. Min Act: -0.0000

Data Index: 368185 (The Pile)

Max Activating Token Index: 370

Text #6

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1475991 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1839833 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1137454 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3492. Min Act: -0.0000

Data Index: 284479 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3179. Min Act: -0.0000

Data Index: 746330 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1545182 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3449. Min Act: -0.0000

Data Index: 718576 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1051848 (The Pile)

Max Activating Token Index: 429

Text #14

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3297. Min Act: -0.0000

Data Index: 575391 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3327. Min Act: -0.0000

Data Index: 775021 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1486840 (The Pile)

Max Activating Token Index: 976

Text #17

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3254. Min Act: -0.0000

Data Index: 1916123 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3008. Min Act: -0.0000

Data Index: 260209 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.3249. Min Act: -0.0000

Data Index: 279542 (The Pile)

Max Activating Token Index: 446