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

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

Neuron 1563 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: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0006

Data Index: 94602 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0265. Min Act: -0.0006

Data Index: 609956 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1278203 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1255791 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0246. Min Act: -0.0006

Data Index: 365885 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0238. Min Act: -0.0006

Data Index: 890315 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1098956 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0239. Min Act: -0.0006

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0235. Min Act: -0.0006

Data Index: 333855 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0223. Min Act: -0.0006

Data Index: 142970 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1287029 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1298363 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1042108 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0231. Min Act: -0.0006

Data Index: 522389 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1133957 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0245. Min Act: -0.0006

Data Index: 178002 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0235. Min Act: -0.0006

Data Index: 865869 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0229. Min Act: -0.0006

Data Index: 996116 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0234. Min Act: -0.0006

Data Index: 938976 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1013620 (C4 (Web Text))

Max Activating Token Index: 746