Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 75 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0003

Data Index: 669626 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0208. Min Act: -0.0003

Data Index: 515323 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0207. Min Act: -0.0003

Data Index: 25265 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0203. Min Act: -0.0003

Data Index: 975832 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0200. Min Act: -0.0003

Data Index: 435441 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0202. Min Act: -0.0003

Data Index: 176066 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1547367 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1181881 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0194. Min Act: -0.0003

Data Index: 626292 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0191. Min Act: -0.0003

Data Index: 787996 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1601712 (Python Code)

Max Activating Token Index: 577

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1269142 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1053591 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0191. Min Act: -0.0003

Data Index: 277198 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1517571 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0184. Min Act: -0.0002

Data Index: 275747 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1068551 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0184. Min Act: -0.0003

Data Index: 492867 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0182. Min Act: -0.0003

Data Index: 339604 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1387430 (Python Code)

Max Activating Token Index: 765