Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2457 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.3987. Min Act: -0.0000

Data Index: 1090138 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.3910. Min Act: -0.0000

Data Index: 1311737 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.2914. Min Act: -0.0000

Data Index: 194885 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.0339. Min Act: -0.0000

Data Index: 456755 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1493673 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.0282. Min Act: -0.0000

Data Index: 115099 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1349551 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.9191. Min Act: -0.0000

Data Index: 176475 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1696789 (The Pile)

Max Activating Token Index: 394

Text #9

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.8294. Min Act: -0.0000

Data Index: 388177 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1409582 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.6290. Min Act: 0.0000

Data Index: 1696951 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.6395. Min Act: -0.0000

Data Index: 200716 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.5794. Min Act: -0.0000

Data Index: 527995 (The Pile)

Max Activating Token Index: 725

Text #14

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1241725 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.7033. Min Act: -0.0000

Data Index: 603369 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.6258. Min Act: -0.0000

Data Index: 124834 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1459329 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.6128. Min Act: -0.0000

Data Index: 155170 (The Pile)

Max Activating Token Index: 1010

Text #19

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.6103. Min Act: -0.0000

Data Index: 247918 (The Pile)

Max Activating Token Index: 194