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

Dataset: The Pile

Neuron 903 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3444. Min Act: -0.0000

Data Index: 72035 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3668. Min Act: -0.0000

Data Index: 246561 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1601048 (The Pile)

Max Activating Token Index: 890

Text #3

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3563. Min Act: -0.0000

Data Index: 132043 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1989449 (The Pile)

Max Activating Token Index: 429

Text #5

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1374921 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1148262 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1886221 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1152129 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1710091 (The Pile)

Max Activating Token Index: 6

Text #10

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1776144 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3318. Min Act: -0.0000

Data Index: 178075 (The Pile)

Max Activating Token Index: 656

Text #12

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1431629 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3291. Min Act: -0.0000

Data Index: 537919 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3451. Min Act: -0.0000

Data Index: 276887 (The Pile)

Max Activating Token Index: 628

Text #15

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3272. Min Act: -0.0000

Data Index: 560260 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3454. Min Act: -0.0000

Data Index: 938591 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1512103 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1051743 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.3966. Min Range: -0.3966

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1568973 (The Pile)

Max Activating Token Index: 759