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

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

Neuron 5921 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: 0.3023. Min Range: -0.3023

Max Act: 0.3023. Min Act: -0.0002

Data Index: 171622 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2685. Min Act: -0.0002

Data Index: 1262330 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2659. Min Act: -0.0002

Data Index: 316385 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2647. Min Act: -0.0002

Data Index: 453239 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2507. Min Act: -0.0002

Data Index: 691989 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2379. Min Act: -0.0002

Data Index: 417041 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2451. Min Act: -0.0002

Data Index: 574886 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2522. Min Act: -0.0002

Data Index: 1162608 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2482. Min Act: -0.0002

Data Index: 839562 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2367. Min Act: -0.0002

Data Index: 1034567 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2302. Min Act: -0.0002

Data Index: 1091064 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2274. Min Act: -0.0002

Data Index: 1198920 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2211. Min Act: -0.0002

Data Index: 132551 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2286. Min Act: -0.0002

Data Index: 984188 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2338. Min Act: -0.0002

Data Index: 263616 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2301. Min Act: -0.0002

Data Index: 801281 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2128. Min Act: -0.0002

Data Index: 852355 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2171. Min Act: -0.0002

Data Index: 794458 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2115. Min Act: -0.0002

Data Index: 372429 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.3023. Min Range: -0.3023

Max Act: 0.2102. Min Act: -0.0002

Data Index: 256666 (C4 (Web Text))

Max Activating Token Index: 725