Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 218 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3230. Min Act: 0.0000

Data Index: 966328 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3218. Min Act: 0.0000

Data Index: 996287 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3220. Min Act: -0.0001

Data Index: 612828 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3228. Min Act: 0.0001

Data Index: 323327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3234. Min Act: -0.0000

Data Index: 838048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3220. Min Act: 0.0001

Data Index: 434338 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3218. Min Act: 0.0002

Data Index: 713060 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3217. Min Act: -0.0000

Data Index: 745554 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3218. Min Act: 0.0000

Data Index: 72611 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3215. Min Act: 0.0001

Data Index: 1324293 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3218. Min Act: 0.0001

Data Index: 798561 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3205. Min Act: 0.0000

Data Index: 481053 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3213. Min Act: 0.0000

Data Index: 246345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1011408 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3212. Min Act: 0.0001

Data Index: 910524 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3238. Min Act: -0.0001

Data Index: 629218 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3216. Min Act: 0.0001

Data Index: 1277715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1266923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3217. Min Act: -0.0000

Data Index: 260386 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3223. Min Act: 0.0001

Data Index: 808199 (C4 (Web Text))

Max Activating Token Index: 1023