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

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

Neuron 3250 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1308. Min Act: -0.0000

Data Index: 921309 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1205. Min Act: -0.0000

Data Index: 577118 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1251. Min Act: -0.0000

Data Index: 685082 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1234248 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1124. Min Act: -0.0000

Data Index: 455432 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1097. Min Act: -0.0000

Data Index: 31086 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1028. Min Act: -0.0000

Data Index: 752962 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0857. Min Act: -0.0000

Data Index: 354470 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1020250 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0964. Min Act: -0.0000

Data Index: 786592 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1047137 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0916. Min Act: -0.0000

Data Index: 417616 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1067320 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0830. Min Act: -0.0000

Data Index: 63002 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1337835 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1246285 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0766. Min Act: -0.0000

Data Index: 17049 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1100124 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0812. Min Act: -0.0000

Data Index: 640962 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1003177 (C4 (Web Text))

Max Activating Token Index: 465