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

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

Neuron 30 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1181506 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1020630 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3914. Min Act: -0.0000

Data Index: 432947 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3417. Min Act: -0.0000

Data Index: 492053 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3672. Min Act: -0.0000

Data Index: 960225 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1116885 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1044663 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1215795 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3280. Min Act: -0.0000

Data Index: 830492 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3052. Min Act: -0.0000

Data Index: 679505 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1130341 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3183. Min Act: -0.0000

Data Index: 835780 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1085814 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3074. Min Act: -0.0000

Data Index: 210396 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2985. Min Act: -0.0000

Data Index: 795796 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3152. Min Act: -0.0000

Data Index: 834836 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2929. Min Act: -0.0000

Data Index: 595201 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1202735 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1051992 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.4004. Min Range: -0.4004

Max Act: 0.2715. Min Act: -0.0000

Data Index: 186273 (C4 (Web Text))

Max Activating Token Index: 519