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

Dataset: The Pile

Neuron 3734 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: 0.8223. Min Range: -0.8223

Max Act: 0.8223. Min Act: -0.0000

Data Index: 687718 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1576178 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1965565 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3127. Min Act: -0.0000

Data Index: 166075 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1282418 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3663. Min Act: -0.0000

Data Index: 711190 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3636. Min Act: -0.0000

Data Index: 621629 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1639630 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1640259 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1735258 (The Pile)

Max Activating Token Index: 428

Text #10

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3347. Min Act: -0.0000

Data Index: 145548 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1272729 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3277. Min Act: -0.0000

Data Index: 670342 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1465218 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1254789 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.2914. Min Act: -0.0000

Data Index: 350349 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3155. Min Act: -0.0000

Data Index: 673462 (The Pile)

Max Activating Token Index: 942

Text #17

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3479. Min Act: -0.0000

Data Index: 954886 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3373. Min Act: -0.0000

Data Index: 246210 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.3011. Min Act: -0.0000

Data Index: 40056 (The Pile)

Max Activating Token Index: 1005