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

Dataset: The Pile

Neuron 4113 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.9708. Min Act: -0.0000

Data Index: 317901 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1292328 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.8107. Min Act: 0.0000

Data Index: 1313256 (The Pile)

Max Activating Token Index: 886

Text #3

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.8274. Min Act: -0.0000

Data Index: 969110 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.8241. Min Act: -0.0000

Data Index: 815473 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.8282. Min Act: -0.0000

Data Index: 496492 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.8220. Min Act: -0.0000

Data Index: 820633 (The Pile)

Max Activating Token Index: 933

Text #7

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1960192 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.8488. Min Act: -0.0000

Data Index: 365771 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7451. Min Act: 0.0001

Data Index: 1748541 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.8712. Min Act: 0.0000

Data Index: 1510663 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7839. Min Act: -0.0000

Data Index: 215658 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7245. Min Act: -0.0000

Data Index: 646809 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1363262 (The Pile)

Max Activating Token Index: 17

Text #14

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7584. Min Act: 0.0000

Data Index: 969179 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7555. Min Act: -0.0000

Data Index: 248909 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1847869 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1477084 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7337. Min Act: -0.0000

Data Index: 177931 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 0.9708. Min Range: -0.9708

Max Act: 0.7517. Min Act: -0.0000

Data Index: 662975 (The Pile)

Max Activating Token Index: 208