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

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

Neuron 1285 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1005879 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1310828 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0204. Min Act: -0.0002

Data Index: 786723 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0221. Min Act: -0.0002

Data Index: 933903 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1024269 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0203. Min Act: -0.0002

Data Index: 991914 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0187. Min Act: -0.0002

Data Index: 226346 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0197. Min Act: -0.0002

Data Index: 462009 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1375598 (Python Code)

Max Activating Token Index: 481

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1259044 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0187. Min Act: -0.0002

Data Index: 21329 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1580667 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1572005 (Python Code)

Max Activating Token Index: 332

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1039808 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0195. Min Act: -0.0002

Data Index: 107244 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0190. Min Act: -0.0002

Data Index: 569782 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1193621 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1346402 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0182. Min Act: -0.0002

Data Index: 351302 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1257908 (C4 (Web Text))

Max Activating Token Index: 215