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

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

Neuron 2773 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0347. Min Act: -0.0003

Data Index: 806216 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0238. Min Act: -0.0003

Data Index: 771158 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1399054 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0208. Min Act: -0.0003

Data Index: 95666 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1574264 (Python Code)

Max Activating Token Index: 496

Text #5

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0205. Min Act: -0.0003

Data Index: 815408 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0200. Min Act: -0.0003

Data Index: 578038 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1521374 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0201. Min Act: -0.0002

Data Index: 60139 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1186061 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1285275 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1315301 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1047567 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1598438 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0190. Min Act: -0.0003

Data Index: 448293 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0192. Min Act: -0.0003

Data Index: 20052 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0176. Min Act: -0.0003

Data Index: 244444 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1282601 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0188. Min Act: -0.0003

Data Index: 154557 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.0347. Min Range: -0.0347

Max Act: 0.0192. Min Act: -0.0003

Data Index: 990430 (C4 (Web Text))

Max Activating Token Index: 281