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

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

Neuron 4473 in Layer 1

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: -0.0003

Data Index: 494967 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0233. Min Act: -0.0003

Data Index: 234963 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0226. Min Act: -0.0003

Data Index: 391625 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1463943 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0219. Min Act: -0.0003

Data Index: 721881 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0206. Min Act: -0.0003

Data Index: 180875 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1170502 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0191. Min Act: -0.0003

Data Index: 551949 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1143026 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0206. Min Act: -0.0003

Data Index: 65200 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0193. Min Act: -0.0003

Data Index: 424587 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0192. Min Act: -0.0002

Data Index: 248903 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1114208 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0188. Min Act: -0.0003

Data Index: 907359 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1338405 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0179. Min Act: -0.0003

Data Index: 366416 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0185. Min Act: -0.0003

Data Index: 757392 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0178. Min Act: -0.0002

Data Index: 188030 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1017752 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1090303 (C4 (Web Text))

Max Activating Token Index: 383