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

Dataset: The Pile

Neuron 4760 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: 0.1289. Min Range: -0.1289

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1589900 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1608189 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1061. Min Act: -0.0000

Data Index: 136072 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1893114 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1667856 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1465797 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1437750 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1038. Min Act: -0.0000

Data Index: 701551 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1266594 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1840164 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0880. Min Act: -0.0000

Data Index: 419835 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1843605 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1233549 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1958034 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1979412 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0994. Min Act: -0.0000

Data Index: 500510 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1879651 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1552199 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1987329 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0949. Min Act: -0.0000

Data Index: 126433 (The Pile)

Max Activating Token Index: 637