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

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

Neuron 3507 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1060805 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1227213 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1267399 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.1549. Min Act: -0.0000

Data Index: 558598 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.1741. Min Act: -0.0000

Data Index: 729689 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.1622. Min Act: -0.0000

Data Index: 650448 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.9662. Min Act: -0.0000

Data Index: 928286 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1063847 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0767. Min Act: -0.0000

Data Index: 674186 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0391. Min Act: -0.0000

Data Index: 364901 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1205449 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.9284. Min Act: -0.0000

Data Index: 352395 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1295580 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0499. Min Act: -0.0000

Data Index: 147946 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0218. Min Act: -0.0000

Data Index: 189891 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0427. Min Act: -0.0000

Data Index: 658059 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 1.6219. Min Range: -1.6219

Max Act: 1.0171. Min Act: -0.0000

Data Index: 771843 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.9477. Min Act: -0.0000

Data Index: 26685 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.8743. Min Act: -0.0000

Data Index: 221144 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 1.6219. Min Range: -1.6219

Max Act: 0.9475. Min Act: -0.0000

Data Index: 385320 (C4 (Web Text))

Max Activating Token Index: 635