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

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

Neuron 400 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: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1599446 (Python Code)

Max Activating Token Index: 1004

Text #1

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0234. Min Act: -0.0002

Data Index: 23862 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0218. Min Act: -0.0002

Data Index: 988884 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0211. Min Act: -0.0002

Data Index: 53381 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0207. Min Act: -0.0002

Data Index: 737027 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1449047 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0210. Min Act: -0.0002

Data Index: 916696 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1428156 (Python Code)

Max Activating Token Index: 141

Text #8

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0203. Min Act: -0.0002

Data Index: 215287 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1649300 (Python Code)

Max Activating Token Index: 855

Text #10

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0201. Min Act: -0.0002

Data Index: 981621 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1063724 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0200. Min Act: -0.0002

Data Index: 161947 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1647081 (Python Code)

Max Activating Token Index: 646

Text #14

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0197. Min Act: -0.0002

Data Index: 298561 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0196. Min Act: -0.0002

Data Index: 513297 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0195. Min Act: -0.0002

Data Index: 313652 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0194. Min Act: -0.0002

Data Index: 830469 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0193. Min Act: -0.0002

Data Index: 979079 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0190. Min Act: -0.0002

Data Index: 562863 (C4 (Web Text))

Max Activating Token Index: 845