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

Dataset: The Pile

Neuron 3512 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1076971 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8468. Min Act: -0.0000

Data Index: 287258 (The Pile)

Max Activating Token Index: 985

Text #2

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1465740 (The Pile)

Max Activating Token Index: 843

Text #3

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1358649 (The Pile)

Max Activating Token Index: 460

Text #4

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1585704 (The Pile)

Max Activating Token Index: 510

Text #5

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6716. Min Act: -0.0000

Data Index: 722366 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1356274 (The Pile)

Max Activating Token Index: 969

Text #7

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1107084 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7420. Min Act: 0.0000

Data Index: 644263 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1930748 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1340087 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1267540 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6820. Min Act: 0.0000

Data Index: 687580 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1534770 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1832005 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6393. Min Act: -0.0000

Data Index: 220872 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6767. Min Act: -0.0000

Data Index: 196622 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6356. Min Act: -0.0000

Data Index: 158714 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1041031 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.6251. Min Act: -0.0000

Data Index: 858423 (The Pile)

Max Activating Token Index: 898