Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 115 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0006

Data Index: 970684 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0218. Min Act: -0.0006

Data Index: 490757 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1512742 (Python Code)

Max Activating Token Index: 49

Text #3

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0213. Min Act: -0.0006

Data Index: 275396 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1190584 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1031827 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0215. Min Act: -0.0006

Data Index: 912262 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0187. Min Act: -0.0006

Data Index: 214632 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0193. Min Act: -0.0006

Data Index: 999565 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0198. Min Act: -0.0006

Data Index: 623010 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0186. Min Act: -0.0006

Data Index: 225468 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0185. Min Act: -0.0006

Data Index: 647937 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1336046 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1623090 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1397441 (Python Code)

Max Activating Token Index: 235

Text #15

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1441709 (Python Code)

Max Activating Token Index: 272

Text #16

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0181. Min Act: -0.0006

Data Index: 649421 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1105746 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1355175 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0178. Min Act: -0.0006

Data Index: 493119 (C4 (Web Text))

Max Activating Token Index: 123