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

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

Neuron 1304 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: 0.0219. Min Range: -0.0219

Max Act: 0.0217. Min Act: -0.0006

Data Index: 566077 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0209. Min Act: -0.0007

Data Index: 92457 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0006

Data Index: 39194 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0006

Data Index: 704442 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0216. Min Act: -0.0006

Data Index: 549279 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0216. Min Act: -0.0006

Data Index: 738220 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0208. Min Act: -0.0006

Data Index: 252377 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1251003 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0212. Min Act: -0.0006

Data Index: 389752 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0215. Min Act: -0.0006

Data Index: 927646 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0205. Min Act: -0.0006

Data Index: 625374 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0203. Min Act: -0.0006

Data Index: 396067 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0204. Min Act: -0.0006

Data Index: 790123 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0208. Min Act: -0.0006

Data Index: 219592 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0198. Min Act: -0.0006

Data Index: 750692 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0203. Min Act: -0.0006

Data Index: 956708 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0208. Min Act: -0.0006

Data Index: 751284 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0203. Min Act: -0.0006

Data Index: 833242 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0206. Min Act: -0.0007

Data Index: 374162 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0200. Min Act: -0.0006

Data Index: 995855 (C4 (Web Text))

Max Activating Token Index: 227