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

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

Neuron 1968 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: 0.0233. Min Range: -0.0233

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1230281 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1207101 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0226. Min Act: -0.0006

Data Index: 68651 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0220. Min Act: -0.0006

Data Index: 487070 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1249223 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0216. Min Act: -0.0006

Data Index: 20083 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0215. Min Act: -0.0006

Data Index: 109743 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0216. Min Act: -0.0006

Data Index: 770876 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1153088 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0211. Min Act: -0.0006

Data Index: 484815 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0204. Min Act: -0.0006

Data Index: 69297 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0202. Min Act: -0.0006

Data Index: 682350 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0202. Min Act: -0.0006

Data Index: 354917 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0200. Min Act: -0.0006

Data Index: 170284 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0200. Min Act: -0.0006

Data Index: 51029 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0190. Min Act: -0.0005

Data Index: 1069047 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0199. Min Act: -0.0006

Data Index: 561928 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0198. Min Act: -0.0006

Data Index: 956593 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1605554 (Python Code)

Max Activating Token Index: 330

Text #19

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0195. Min Act: -0.0006

Data Index: 475137 (C4 (Web Text))

Max Activating Token Index: 503