Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1771 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0246. Min Act: -0.0003

Data Index: 966390 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0254. Min Act: -0.0003

Data Index: 482860 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1329756 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1110965 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1068356 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1226577 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0213. Min Act: -0.0003

Data Index: 312355 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0228. Min Act: -0.0003

Data Index: 10612 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1097405 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0200. Min Act: -0.0003

Data Index: 819719 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0233. Min Act: -0.0003

Data Index: 766479 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0205. Min Act: -0.0003

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0207. Min Act: -0.0003

Data Index: 134784 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1609615 (Python Code)

Max Activating Token Index: 830

Text #14

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0206. Min Act: -0.0003

Data Index: 843967 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0228. Min Act: -0.0003

Data Index: 186254 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1653299 (Python Code)

Max Activating Token Index: 471

Text #17

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1286850 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1451828 (Python Code)

Max Activating Token Index: 884

Text #19

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0206. Min Act: -0.0003

Data Index: 378907 (C4 (Web Text))

Max Activating Token Index: 81