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

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

Neuron 828 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0370. Min Act: -0.0006

Data Index: 1239795 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0310. Min Act: -0.0006

Data Index: 992688 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0282. Min Act: -0.0006

Data Index: 911274 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0243. Min Act: -0.0006

Data Index: 349126 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1118511 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0235. Min Act: -0.0006

Data Index: 739962 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0228. Min Act: -0.0006

Data Index: 653256 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1051486 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0231. Min Act: -0.0006

Data Index: 16098 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0220. Min Act: -0.0006

Data Index: 620719 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0225. Min Act: -0.0006

Data Index: 973170 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0225. Min Act: -0.0006

Data Index: 478859 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1178069 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0229. Min Act: -0.0006

Data Index: 885632 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1308836 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0224. Min Act: -0.0006

Data Index: 531007 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0217. Min Act: -0.0006

Data Index: 47251 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0221. Min Act: -0.0006

Data Index: 106597 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0221. Min Act: -0.0006

Data Index: 751168 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0221. Min Act: -0.0006

Data Index: 64373 (C4 (Web Text))

Max Activating Token Index: 105