Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1497 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1595276 (Python Code)

Max Activating Token Index: 646

Text #1

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0205. Min Act: -0.0002

Data Index: 666264 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0192. Min Act: -0.0003

Data Index: 141615 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0198. Min Act: -0.0002

Data Index: 198350 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0196. Min Act: -0.0003

Data Index: 540924 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1560812 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0181. Min Act: -0.0002

Data Index: 714056 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1565958 (Python Code)

Max Activating Token Index: 529

Text #8

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1474796 (Python Code)

Max Activating Token Index: 315

Text #9

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1237978 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1046495 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1026338 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1050637 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0169. Min Act: -0.0003

Data Index: 952412 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0166. Min Act: -0.0002

Data Index: 12003 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0164. Min Act: -0.0003

Data Index: 26 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1452639 (Python Code)

Max Activating Token Index: 860

Text #17

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1484870 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1585064 (Python Code)

Max Activating Token Index: 659

Text #19

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0160. Min Act: -0.0002

Data Index: 613593 (C4 (Web Text))

Max Activating Token Index: 972