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

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

Neuron 1096 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0256. Min Act: -0.0006

Data Index: 243307 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0245. Min Act: -0.0006

Data Index: 461305 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0231. Min Act: -0.0006

Data Index: 630841 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1084761 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0219. Min Act: -0.0006

Data Index: 248748 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0223. Min Act: -0.0006

Data Index: 596764 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0220. Min Act: -0.0006

Data Index: 280199 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0213. Min Act: -0.0006

Data Index: 520107 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1099624 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1225945 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1236627 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0201. Min Act: -0.0006

Data Index: 451034 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1379681 (Python Code)

Max Activating Token Index: 231

Text #13

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0203. Min Act: -0.0006

Data Index: 531280 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1407027 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0212. Min Act: -0.0006

Data Index: 187803 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0211. Min Act: -0.0006

Data Index: 896367 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0206. Min Act: -0.0006

Data Index: 255427 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1315126 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1237740 (C4 (Web Text))

Max Activating Token Index: 77