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

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

Neuron 2041 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0239. Min Act: -0.0006

Data Index: 231775 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0200. Min Act: -0.0005

Data Index: 934276 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0194. Min Act: -0.0005

Data Index: 436713 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0184. Min Act: -0.0005

Data Index: 94370 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0187. Min Act: -0.0005

Data Index: 621127 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0178. Min Act: -0.0006

Data Index: 360667 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0185. Min Act: -0.0005

Data Index: 118365 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0188. Min Act: -0.0005

Data Index: 534323 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0184. Min Act: -0.0005

Data Index: 896622 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0187. Min Act: -0.0005

Data Index: 1238983 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0183. Min Act: -0.0005

Data Index: 489968 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0183. Min Act: -0.0005

Data Index: 751854 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0182. Min Act: -0.0005

Data Index: 822383 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0181. Min Act: -0.0005

Data Index: 1272738 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0178. Min Act: -0.0005

Data Index: 169340 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0180. Min Act: -0.0005

Data Index: 94214 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1266004 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0179. Min Act: -0.0005

Data Index: 1334648 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0171. Min Act: -0.0005

Data Index: 791579 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0177. Min Act: -0.0005

Data Index: 607888 (C4 (Web Text))

Max Activating Token Index: 586