Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 106 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0242. Min Act: -0.0006

Data Index: 557764 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0231. Min Act: -0.0006

Data Index: 863183 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0231. Min Act: -0.0006

Data Index: 227994 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0226. Min Act: -0.0006

Data Index: 627874 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0240. Min Act: -0.0006

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0247. Min Act: -0.0006

Data Index: 1256637 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0229. Min Act: -0.0006

Data Index: 835841 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0221. Min Act: -0.0006

Data Index: 532264 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0230. Min Act: -0.0006

Data Index: 117868 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0240. Min Act: -0.0006

Data Index: 762393 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1072814 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0235. Min Act: -0.0006

Data Index: 305773 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0219. Min Act: -0.0006

Data Index: 280610 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0219. Min Act: -0.0006

Data Index: 554140 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0217. Min Act: -0.0006

Data Index: 101174 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0216. Min Act: -0.0006

Data Index: 762334 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0202. Min Act: -0.0006

Data Index: 844123 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1250656 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0209. Min Act: -0.0006

Data Index: 736768 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0208. Min Act: -0.0006

Data Index: 452744 (C4 (Web Text))

Max Activating Token Index: 979