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

Dataset: The Pile

Neuron 566 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.4096. Min Act: -0.0000

Data Index: 1711430 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0451. Min Act: -0.0000

Data Index: 670956 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1403848 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1817764 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.8464. Min Act: -0.0000

Data Index: 31160 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1996067 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1853225 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1092083 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1137454 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1071008 (The Pile)

Max Activating Token Index: 814

Text #10

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.7297. Min Act: -0.0000

Data Index: 4502 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.6817. Min Act: -0.0000

Data Index: 761828 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1420277 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1370299 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1596612 (The Pile)

Max Activating Token Index: 954

Text #15

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1566734 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.7237. Min Act: -0.0000

Data Index: 101917 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1438730 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.6919. Min Act: -0.0000

Data Index: 549885 (The Pile)

Max Activating Token Index: 914

Text #19

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.6992. Min Act: -0.0000

Data Index: 527413 (The Pile)

Max Activating Token Index: 861