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

Dataset: The Pile

Neuron 3889 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1246993 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1115164 (The Pile)

Max Activating Token Index: 6

Text #2

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3832. Min Act: -0.0000

Data Index: 928931 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3807. Min Act: 0.0000

Data Index: 1543201 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1590969 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3599. Min Act: 0.0000

Data Index: 1145578 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1169420 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1727328 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3583. Min Act: 0.0000

Data Index: 647550 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1398817 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3668. Min Act: 0.0000

Data Index: 1640225 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3884. Min Act: 0.0000

Data Index: 1649057 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1664788 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1024417 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1819468 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1350031 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3506. Min Act: -0.0000

Data Index: 744014 (The Pile)

Max Activating Token Index: 166

Text #17

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3170. Min Act: -0.0000

Data Index: 250450 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1503092 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 0.4362. Min Range: -0.4362

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1104330 (The Pile)

Max Activating Token Index: 76