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

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

Neuron 75 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: 0.0223. Min Range: -0.0223

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1190799 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0222. Min Act: -0.0007

Data Index: 1132648 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0220. Min Act: -0.0006

Data Index: 742288 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0216. Min Act: -0.0006

Data Index: 956857 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0214. Min Act: -0.0005

Data Index: 1461503 (Python Code)

Max Activating Token Index: 985

Text #5

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0210. Min Act: -0.0006

Data Index: 190807 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0209. Min Act: -0.0006

Data Index: 963951 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0209. Min Act: -0.0006

Data Index: 488927 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0209. Min Act: -0.0006

Data Index: 15086 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0213. Min Act: -0.0007

Data Index: 411089 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0208. Min Act: -0.0006

Data Index: 585087 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0208. Min Act: -0.0006

Data Index: 253231 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0204. Min Act: -0.0006

Data Index: 705248 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1304500 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1060082 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0201. Min Act: -0.0006

Data Index: 144557 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0201. Min Act: -0.0006

Data Index: 11274 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1247761 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0204. Min Act: -0.0006

Data Index: 178205 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1188671 (C4 (Web Text))

Max Activating Token Index: 637