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

Dataset: The Pile

Neuron 2427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1533249 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1498786 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.8212. Min Act: -0.0000

Data Index: 601009 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7687. Min Act: -0.0000

Data Index: 134069 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.8085. Min Act: -0.0000

Data Index: 606991 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7928. Min Act: -0.0000

Data Index: 817064 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1860403 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1393482 (The Pile)

Max Activating Token Index: 930

Text #8

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1447785 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7453. Min Act: -0.0000

Data Index: 351776 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7232. Min Act: -0.0000

Data Index: 976080 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7630. Min Act: -0.0000

Data Index: 442297 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1321809 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.6769. Min Act: -0.0000

Data Index: 328140 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.6891. Min Act: -0.0000

Data Index: 828591 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1296373 (The Pile)

Max Activating Token Index: 136

Text #16

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1385110 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.6807. Min Act: -0.0000

Data Index: 290741 (The Pile)

Max Activating Token Index: 492

Text #18

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7036. Min Act: -0.0000

Data Index: 674611 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.6998. Min Act: -0.0000

Data Index: 747259 (The Pile)

Max Activating Token Index: 991