Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3851 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0002

Data Index: 126252 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1186887 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0245. Min Act: -0.0002

Data Index: 522440 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1266331 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0236. Min Act: -0.0002

Data Index: 929745 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0239. Min Act: -0.0002

Data Index: 638617 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0229. Min Act: -0.0002

Data Index: 476139 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0228. Min Act: -0.0002

Data Index: 222157 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0222. Min Act: -0.0002

Data Index: 558103 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0206. Min Act: -0.0002

Data Index: 955137 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0210. Min Act: -0.0002

Data Index: 974826 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0210. Min Act: -0.0002

Data Index: 840064 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0214. Min Act: -0.0002

Data Index: 638740 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1205131 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0203. Min Act: -0.0002

Data Index: 583360 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0198. Min Act: -0.0002

Data Index: 727423 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1146416 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1111899 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0198. Min Act: -0.0002

Data Index: 529562 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0198. Min Act: -0.0002

Data Index: 725447 (C4 (Web Text))

Max Activating Token Index: 324