Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3087 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0256. Min Act: -0.0003

Data Index: 126709 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1098275 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1584604 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0227. Min Act: -0.0003

Data Index: 709317 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0233. Min Act: -0.0003

Data Index: 823286 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0232. Min Act: -0.0003

Data Index: 558246 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1118004 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1623565 (Python Code)

Max Activating Token Index: 238

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1477538 (Python Code)

Max Activating Token Index: 535

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0215. Min Act: -0.0003

Data Index: 213737 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0245. Min Act: -0.0003

Data Index: 637373 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1030625 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1218558 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0239. Min Act: -0.0003

Data Index: 911238 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0217. Min Act: -0.0003

Data Index: 872276 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1622637 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0215. Min Act: -0.0003

Data Index: 339036 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0234. Min Act: -0.0003

Data Index: 886629 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0224. Min Act: -0.0004

Data Index: 597329 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0235. Min Act: -0.0003

Data Index: 329739 (C4 (Web Text))

Max Activating Token Index: 500