Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 406 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0004

Data Index: 133337 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0201. Min Act: -0.0004

Data Index: 1117566 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0229. Min Act: -0.0004

Data Index: 128119 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0186. Min Act: -0.0004

Data Index: 303714 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0212. Min Act: -0.0004

Data Index: 822999 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0174. Min Act: -0.0004

Data Index: 977385 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0160. Min Act: -0.0004

Data Index: 287806 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0207. Min Act: -0.0004

Data Index: 728667 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0193. Min Act: -0.0004

Data Index: 1517448 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0177. Min Act: -0.0004

Data Index: 826336 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0180. Min Act: -0.0004

Data Index: 248529 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0190. Min Act: -0.0004

Data Index: 208291 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0178. Min Act: -0.0004

Data Index: 1056863 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0004

Data Index: 413071 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0184. Min Act: -0.0004

Data Index: 534059 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0191. Min Act: -0.0004

Data Index: 1495379 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0185. Min Act: -0.0004

Data Index: 741986 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0199. Min Act: -0.0004

Data Index: 1249229 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0195. Min Act: -0.0004

Data Index: 41334 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0152. Min Act: -0.0004

Data Index: 539200 (C4 (Web Text))

Max Activating Token Index: 820