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

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

Neuron 5040 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: 0.6720. Min Range: -0.6720

Max Act: 0.6720. Min Act: -0.0002

Data Index: 271636 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.6256. Min Act: -0.0002

Data Index: 1006760 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5828. Min Act: -0.0002

Data Index: 670298 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5933. Min Act: -0.0002

Data Index: 334139 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.6496. Min Act: -0.0002

Data Index: 966899 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5991. Min Act: -0.0002

Data Index: 665498 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5852. Min Act: -0.0002

Data Index: 568727 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5514. Min Act: -0.0002

Data Index: 1304020 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5410. Min Act: -0.0002

Data Index: 47529 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.6193. Min Act: -0.0002

Data Index: 760311 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5355. Min Act: -0.0002

Data Index: 203348 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5871. Min Act: -0.0002

Data Index: 1325683 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5329. Min Act: -0.0002

Data Index: 857632 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5322. Min Act: -0.0002

Data Index: 938007 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5357. Min Act: -0.0002

Data Index: 611573 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5368. Min Act: -0.0002

Data Index: 1107287 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5321. Min Act: -0.0002

Data Index: 1271541 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.5089. Min Act: -0.0002

Data Index: 73524 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.6197. Min Act: -0.0002

Data Index: 1152162 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.6720. Min Range: -0.6720

Max Act: 0.4808. Min Act: -0.0002

Data Index: 501611 (C4 (Web Text))

Max Activating Token Index: 667