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

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

Neuron 64 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0003

Data Index: 520195 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0277. Min Act: -0.0003

Data Index: 418253 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0252. Min Act: -0.0003

Data Index: 628153 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1207168 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0236. Min Act: -0.0003

Data Index: 824888 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0234. Min Act: -0.0003

Data Index: 150390 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0237. Min Act: -0.0003

Data Index: 721901 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0238. Min Act: -0.0003

Data Index: 130000 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0224. Min Act: -0.0003

Data Index: 161412 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0232. Min Act: -0.0003

Data Index: 321495 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1265721 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0219. Min Act: -0.0003

Data Index: 910081 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1340469 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1038538 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0222. Min Act: -0.0003

Data Index: 97909 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0206. Min Act: -0.0003

Data Index: 788609 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1060843 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1189380 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0228. Min Act: -0.0003

Data Index: 103442 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0224. Min Act: -0.0003

Data Index: 435033 (C4 (Web Text))

Max Activating Token Index: 550