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

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

Neuron 2010 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1175015 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0227. Min Act: -0.0006

Data Index: 208112 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1215893 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0242. Min Act: -0.0006

Data Index: 835620 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0224. Min Act: -0.0006

Data Index: 71407 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0222. Min Act: -0.0005

Data Index: 643835 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0224. Min Act: -0.0006

Data Index: 650619 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0223. Min Act: -0.0005

Data Index: 812768 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1351220 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0224. Min Act: -0.0006

Data Index: 174316 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0228. Min Act: -0.0006

Data Index: 388640 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0217. Min Act: -0.0005

Data Index: 637338 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0215. Min Act: -0.0006

Data Index: 177587 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0215. Min Act: -0.0006

Data Index: 297313 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1146874 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0212. Min Act: -0.0005

Data Index: 198112 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0196. Min Act: -0.0006

Data Index: 156613 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0205. Min Act: -0.0005

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1148068 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0196. Min Act: -0.0006

Data Index: 693733 (C4 (Web Text))

Max Activating Token Index: 219