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

Dataset: The Pile

Neuron 3898 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: 3.6359. Min Range: -3.6359

Max Act: 3.6359. Min Act: -0.0000

Data Index: 527553 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.3355. Min Act: -0.0000

Data Index: 912929 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.1662. Min Act: -0.0001

Data Index: 1969578 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9475. Min Act: -0.0000

Data Index: 877123 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9894. Min Act: -0.0000

Data Index: 488065 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.3174. Min Act: -0.0000

Data Index: 1252449 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.8546. Min Act: -0.0000

Data Index: 1651949 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.1321. Min Act: -0.0000

Data Index: 1807686 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9241. Min Act: -0.0000

Data Index: 1990396 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9409. Min Act: -0.0000

Data Index: 1583975 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9956. Min Act: -0.0000

Data Index: 335556 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.8481. Min Act: -0.0000

Data Index: 356748 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.1020. Min Act: -0.0000

Data Index: 855824 (The Pile)

Max Activating Token Index: 879

Text #13

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.8057. Min Act: -0.0000

Data Index: 392372 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.8382. Min Act: -0.0000

Data Index: 1887715 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.0480. Min Act: -0.0000

Data Index: 1334514 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.7822. Min Act: -0.0000

Data Index: 990535 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.6710. Min Act: -0.0000

Data Index: 284376 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.8872. Min Act: -0.0000

Data Index: 991506 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.6045. Min Act: -0.0000

Data Index: 629166 (The Pile)

Max Activating Token Index: 670