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

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

Neuron 315 in Layer 1

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: 0.0230. Min Act: -0.0006

Data Index: 978304 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0233. Min Act: -0.0006

Data Index: 840177 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0215. Min Act: -0.0006

Data Index: 716218 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1130298 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1324869 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1254804 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0217. Min Act: -0.0006

Data Index: 145227 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0212. Min Act: -0.0006

Data Index: 310510 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0212. Min Act: -0.0006

Data Index: 182478 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0216. Min Act: -0.0006

Data Index: 104703 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1200746 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0211. Min Act: -0.0006

Data Index: 167691 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0205. Min Act: -0.0006

Data Index: 49513 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0203. Min Act: -0.0006

Data Index: 385389 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0202. Min Act: -0.0006

Data Index: 76330 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0206. Min Act: -0.0006

Data Index: 171082 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0211. Min Act: -0.0006

Data Index: 649483 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0210. Min Act: -0.0006

Data Index: 770391 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1332339 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0205. Min Act: -0.0006

Data Index: 532569 (C4 (Web Text))

Max Activating Token Index: 198