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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1518 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.6036. Min Act: -0.0000

Data Index: 368776 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.4841. Min Act: 0.0000

Data Index: 143825 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.4694. Min Act: -0.0000

Data Index: 598070 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.4214. Min Act: -0.0000

Data Index: 801204 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3874. Min Act: -0.0000

Data Index: 360768 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3758. Min Act: -0.0000

Data Index: 111648 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3779. Min Act: -0.0000

Data Index: 394726 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3887. Min Act: -0.0000

Data Index: 619729 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3544. Min Act: -0.0000

Data Index: 475788 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3398. Min Act: -0.0000

Data Index: 214701 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3333. Min Act: -0.0000

Data Index: 579180 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3312. Min Act: -0.0000

Data Index: 536858 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3236. Min Act: -0.0000

Data Index: 471059 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1249497 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3182. Min Act: -0.0000

Data Index: 966851 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1262048 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1038178 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3225. Min Act: -0.0000

Data Index: 623815 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3199. Min Act: -0.0000

Data Index: 164513 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.6036. Min Range: -0.6036

Max Act: 0.3171. Min Act: -0.0000

Data Index: 49577 (C4 (Web Text))

Max Activating Token Index: 595