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

Dataset: The Pile

Neuron 795 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.4884. Min Act: -0.0000

Data Index: 245137 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1221304 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1482. Min Act: -0.0000

Data Index: 22695 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8611. Min Act: -0.0000

Data Index: 887548 (The Pile)

Max Activating Token Index: 870

Text #4

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1093663 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1829560 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9462. Min Act: -0.0000

Data Index: 511190 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1529156 (The Pile)

Max Activating Token Index: 636

Text #8

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9254. Min Act: -0.0000

Data Index: 786691 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1807192 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9059. Min Act: -0.0000

Data Index: 666435 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1034251 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1843326 (The Pile)

Max Activating Token Index: 756

Text #13

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1400728 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1096400 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9299. Min Act: -0.0000

Data Index: 815896 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1634366 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1032008 (The Pile)

Max Activating Token Index: 35

Text #18

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.9198. Min Act: -0.0000

Data Index: 656380 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 1.4884. Min Range: -1.4884

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1720782 (The Pile)

Max Activating Token Index: 745