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

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

Neuron 228 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0229. Min Act: -0.0006

Data Index: 269412 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0224. Min Act: -0.0006

Data Index: 685278 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0217. Min Act: -0.0006

Data Index: 145780 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1330453 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1129888 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0204. Min Act: -0.0005

Data Index: 1086034 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0195. Min Act: -0.0006

Data Index: 102553 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0191. Min Act: -0.0006

Data Index: 821527 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0190. Min Act: -0.0006

Data Index: 242006 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0187. Min Act: -0.0006

Data Index: 462874 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0191. Min Act: -0.0006

Data Index: 175657 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0195. Min Act: -0.0006

Data Index: 800113 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1249275 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0190. Min Act: -0.0006

Data Index: 618460 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0186. Min Act: -0.0006

Data Index: 926705 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0185. Min Act: -0.0006

Data Index: 176931 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0184. Min Act: -0.0006

Data Index: 46409 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1352521 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0183. Min Act: -0.0006

Data Index: 426468 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1121130 (C4 (Web Text))

Max Activating Token Index: 791