Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 96 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1310062 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1610589 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1137915 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1642349 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1506200 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0222. Min Act: -0.0006

Data Index: 658705 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0225. Min Act: -0.0006

Data Index: 662156 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0231. Min Act: -0.0006

Data Index: 470874 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1411728 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0228. Min Act: -0.0006

Data Index: 294868 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1044117 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0216. Min Act: -0.0006

Data Index: 177744 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0211. Min Act: -0.0006

Data Index: 702197 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0207. Min Act: -0.0006

Data Index: 470933 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1057963 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0211. Min Act: -0.0006

Data Index: 247008 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1577079 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0194. Min Act: -0.0006

Data Index: 19764 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0200. Min Act: -0.0006

Data Index: 299792 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1491861 (Python Code)

Max Activating Token Index: 1023