Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 505 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0292. Min Act: -0.0004

Data Index: 672502 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0004

Data Index: 718377 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0237. Min Act: -0.0004

Data Index: 1205908 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0231. Min Act: -0.0004

Data Index: 285887 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0189. Min Act: -0.0004

Data Index: 316016 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0184. Min Act: -0.0004

Data Index: 931700 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0205. Min Act: -0.0004

Data Index: 203013 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0229. Min Act: -0.0004

Data Index: 537937 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0203. Min Act: -0.0004

Data Index: 226496 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0203. Min Act: -0.0004

Data Index: 2034 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0200. Min Act: -0.0004

Data Index: 848288 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0203. Min Act: -0.0004

Data Index: 350138 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0198. Min Act: -0.0004

Data Index: 454379 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0207. Min Act: -0.0004

Data Index: 1099874 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0172. Min Act: -0.0004

Data Index: 779912 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0200. Min Act: -0.0004

Data Index: 198364 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0196. Min Act: -0.0004

Data Index: 595202 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0213. Min Act: -0.0004

Data Index: 903965 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0223. Min Act: -0.0004

Data Index: 805080 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0183. Min Act: -0.0004

Data Index: 199854 (C4 (Web Text))

Max Activating Token Index: 78