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

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

Neuron 3110 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0002

Data Index: 451682 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0211. Min Act: -0.0002

Data Index: 881014 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0213. Min Act: -0.0002

Data Index: 862870 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0210. Min Act: -0.0002

Data Index: 837677 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1105920 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1128484 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1247473 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0189. Min Act: -0.0002

Data Index: 995240 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0184. Min Act: -0.0002

Data Index: 95880 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0187. Min Act: -0.0002

Data Index: 358767 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1341883 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0181. Min Act: -0.0002

Data Index: 661507 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0172. Min Act: -0.0002

Data Index: 262678 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0182. Min Act: -0.0002

Data Index: 897553 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0182. Min Act: -0.0002

Data Index: 740487 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1337206 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0174. Min Act: -0.0002

Data Index: 675855 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0176. Min Act: -0.0002

Data Index: 32084 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0175. Min Act: -0.0002

Data Index: 208521 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1258597 (C4 (Web Text))

Max Activating Token Index: 445