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

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

Neuron 327 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: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0003

Data Index: 265987 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0246. Min Act: -0.0003

Data Index: 971713 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1284452 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0214. Min Act: -0.0003

Data Index: 307629 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0216. Min Act: -0.0003

Data Index: 989497 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0220. Min Act: -0.0003

Data Index: 13153 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0201. Min Act: -0.0003

Data Index: 728623 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0213. Min Act: -0.0003

Data Index: 194996 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0216. Min Act: -0.0003

Data Index: 187648 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0206. Min Act: -0.0002

Data Index: 442771 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0202. Min Act: -0.0002

Data Index: 596375 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0198. Min Act: -0.0003

Data Index: 3163 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0198. Min Act: -0.0003

Data Index: 334356 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1016291 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0192. Min Act: -0.0003

Data Index: 189443 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1224686 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0190. Min Act: -0.0003

Data Index: 586761 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1228054 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1008188 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0191. Min Act: -0.0003

Data Index: 15287 (C4 (Web Text))

Max Activating Token Index: 895