Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2025 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0239. Min Act: -0.0002

Data Index: 947942 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0232. Min Act: -0.0002

Data Index: 395113 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0229. Min Act: -0.0002

Data Index: 46957 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0224. Min Act: -0.0002

Data Index: 399960 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0226. Min Act: -0.0002

Data Index: 474996 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1181951 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0210. Min Act: -0.0002

Data Index: 786786 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0208. Min Act: -0.0002

Data Index: 635559 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1258748 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1265362 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0206. Min Act: -0.0002

Data Index: 468124 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0201. Min Act: -0.0002

Data Index: 239816 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0195. Min Act: -0.0002

Data Index: 427778 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0199. Min Act: -0.0002

Data Index: 380817 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1131922 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0198. Min Act: -0.0002

Data Index: 675185 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1238042 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0192. Min Act: -0.0002

Data Index: 78660 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1172785 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0192. Min Act: -0.0002

Data Index: 339959 (C4 (Web Text))

Max Activating Token Index: 754