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

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

Neuron 2746 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: 0.0259. Min Range: -0.0259

Max Act: 0.0234. Min Act: -0.0004

Data Index: 706316 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0226. Min Act: -0.0004

Data Index: 73120 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0004

Data Index: 1225952 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0232. Min Act: -0.0004

Data Index: 1313158 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0214. Min Act: -0.0004

Data Index: 732823 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0004

Data Index: 665179 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0219. Min Act: -0.0004

Data Index: 87081 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0201. Min Act: -0.0004

Data Index: 825332 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0203. Min Act: -0.0004

Data Index: 281880 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0162. Min Act: -0.0004

Data Index: 260544 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0200. Min Act: -0.0004

Data Index: 830798 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0206. Min Act: -0.0004

Data Index: 360157 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0184. Min Act: -0.0004

Data Index: 1172588 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0189. Min Act: -0.0004

Data Index: 1044073 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0173. Min Act: -0.0004

Data Index: 207017 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0191. Min Act: -0.0004

Data Index: 417415 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0182. Min Act: -0.0004

Data Index: 545826 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0190. Min Act: -0.0004

Data Index: 771770 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0187. Min Act: -0.0004

Data Index: 1262707 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0194. Min Act: -0.0004

Data Index: 667099 (C4 (Web Text))

Max Activating Token Index: 308