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

Dataset: The Pile

Neuron 4256 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0264. Min Act: -0.0000

Data Index: 1892915 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0248. Min Act: -0.0000

Data Index: 766596 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0198. Min Act: -0.0000

Data Index: 1172509 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0198. Min Act: -0.0000

Data Index: 897554 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0198. Min Act: -0.0000

Data Index: 241522 (The Pile)

Max Activating Token Index: 36

Text #5

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0220. Min Act: -0.0000

Data Index: 941015 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0205. Min Act: -0.0000

Data Index: 1075258 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0201. Min Act: -0.0000

Data Index: 1541728 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0186. Min Act: -0.0000

Data Index: 1415475 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0196. Min Act: -0.0000

Data Index: 1417175 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0192. Min Act: -0.0000

Data Index: 641516 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0206. Min Act: -0.0000

Data Index: 692689 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0195. Min Act: -0.0000

Data Index: 1972898 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0185. Min Act: -0.0000

Data Index: 199370 (The Pile)

Max Activating Token Index: 39

Text #14

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0182. Min Act: -0.0000

Data Index: 1138902 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0189. Min Act: -0.0000

Data Index: 1530882 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0188. Min Act: -0.0000

Data Index: 1065310 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0182. Min Act: -0.0000

Data Index: 1738601 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0165. Min Act: -0.0000

Data Index: 111941 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0194. Min Act: -0.0000

Data Index: 1209963 (The Pile)

Max Activating Token Index: 227