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

Dataset: The Pile

Neuron 951 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.6190. Min Act: -0.0000

Data Index: 824733 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.6821. Min Act: -0.0000

Data Index: 1822044 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.6308. Min Act: -0.0000

Data Index: 469862 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.4739. Min Act: -0.0000

Data Index: 1291368 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.5378. Min Act: -0.0000

Data Index: 738862 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.3911. Min Act: -0.0000

Data Index: 1245623 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1746817 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1698200 (The Pile)

Max Activating Token Index: 781

Text #8

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.0322. Min Act: -0.0000

Data Index: 968303 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9804. Min Act: -0.0000

Data Index: 680369 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1821161 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1730248 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9015. Min Act: -0.0000

Data Index: 936565 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.0370. Min Act: -0.0000

Data Index: 638481 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9884. Min Act: -0.0000

Data Index: 771976 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9671. Min Act: -0.0000

Data Index: 578387 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.0184. Min Act: -0.0000

Data Index: 1807799 (The Pile)

Max Activating Token Index: 994

Text #17

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9677. Min Act: -0.0000

Data Index: 313006 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 1.6821. Min Range: -1.6821

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1143434 (The Pile)

Max Activating Token Index: 1010

Text #19

Max Range: 1.6821. Min Range: -1.6821

Max Act: 1.0086. Min Act: -0.0000

Data Index: 430594 (The Pile)

Max Activating Token Index: 111