Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2182 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0002

Data Index: 458407 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0255. Min Act: -0.0002

Data Index: 365236 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1434234 (Python Code)

Max Activating Token Index: 662

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0261. Min Act: -0.0002

Data Index: 984842 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0250. Min Act: -0.0002

Data Index: 663029 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0255. Min Act: -0.0002

Data Index: 562597 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0239. Min Act: -0.0002

Data Index: 505845 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0239. Min Act: -0.0002

Data Index: 385684 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0235. Min Act: -0.0002

Data Index: 320761 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0229. Min Act: -0.0002

Data Index: 865722 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0230. Min Act: -0.0002

Data Index: 727630 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1254391 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0210. Min Act: -0.0002

Data Index: 278556 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0223. Min Act: -0.0002

Data Index: 687869 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1326133 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0215. Min Act: -0.0002

Data Index: 911541 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0219. Min Act: -0.0002

Data Index: 125617 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0218. Min Act: -0.0002

Data Index: 81114 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0221. Min Act: -0.0002

Data Index: 421647 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0210. Min Act: -0.0002

Data Index: 198233 (C4 (Web Text))

Max Activating Token Index: 412