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

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

Neuron 3598 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0259. Min Act: -0.0003

Data Index: 507950 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0270. Min Act: -0.0003

Data Index: 511495 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0238. Min Act: -0.0003

Data Index: 826977 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0252. Min Act: -0.0003

Data Index: 804234 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1006789 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0243. Min Act: -0.0003

Data Index: 516946 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0254. Min Act: -0.0003

Data Index: 786240 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1050876 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0247. Min Act: -0.0003

Data Index: 558637 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0243. Min Act: -0.0003

Data Index: 173922 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1342463 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1212013 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0245. Min Act: -0.0003

Data Index: 999371 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0249. Min Act: -0.0003

Data Index: 799012 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1071132 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1194098 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0238. Min Act: -0.0003

Data Index: 631630 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0238. Min Act: -0.0004

Data Index: 776828 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1208293 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0236. Min Act: -0.0003

Data Index: 429245 (C4 (Web Text))

Max Activating Token Index: 163