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

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

Neuron 1413 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: 0.0223. Min Range: -0.0223

Max Act: 0.0223. Min Act: -0.0006

Data Index: 443016 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1316627 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0193. Min Act: -0.0006

Data Index: 95932 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0196. Min Act: -0.0006

Data Index: 42449 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1335523 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0199. Min Act: -0.0006

Data Index: 866876 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0192. Min Act: -0.0006

Data Index: 243569 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0187. Min Act: -0.0006

Data Index: 740853 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0185. Min Act: -0.0006

Data Index: 746422 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0188. Min Act: -0.0006

Data Index: 544147 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0191. Min Act: -0.0006

Data Index: 812689 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0191. Min Act: -0.0006

Data Index: 370367 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1223548 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0190. Min Act: -0.0006

Data Index: 127342 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0177. Min Act: -0.0006

Data Index: 764325 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1197703 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0181. Min Act: -0.0005

Data Index: 1040525 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0184. Min Act: -0.0006

Data Index: 91954 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0184. Min Act: -0.0006

Data Index: 626286 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0176. Min Act: -0.0006

Data Index: 365417 (C4 (Web Text))

Max Activating Token Index: 597