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

Dataset: The Pile

Neuron 2735 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: 0.4136. Min Range: -0.4136

Max Act: 0.4136. Min Act: -0.0000

Data Index: 627529 (The Pile)

Max Activating Token Index: 106

Text #1

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3824. Min Act: -0.0000

Data Index: 45224 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1714447 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1749775 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3466. Min Act: 0.0000

Data Index: 551291 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1225180 (The Pile)

Max Activating Token Index: 458

Text #6

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1028478 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1477899 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3619. Min Act: 0.0002

Data Index: 966203 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1892874 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3485. Min Act: 0.0000

Data Index: 577500 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3550. Min Act: -0.0000

Data Index: 718050 (The Pile)

Max Activating Token Index: 431

Text #12

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1003762 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3479. Min Act: 0.0000

Data Index: 352829 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1093351 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3265. Min Act: -0.0000

Data Index: 132100 (The Pile)

Max Activating Token Index: 257

Text #16

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1684117 (The Pile)

Max Activating Token Index: 983

Text #17

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3366. Min Act: 0.0000

Data Index: 701430 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3105. Min Act: 0.0000

Data Index: 1387854 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 0.4136. Min Range: -0.4136

Max Act: 0.3312. Min Act: -0.0000

Data Index: 913384 (The Pile)

Max Activating Token Index: 603