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

Dataset: The Pile

Neuron 1824 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: 0.7807. Min Range: -0.7807

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1205928 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1157807 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.7445. Min Act: -0.0000

Data Index: 164247 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6602. Min Act: -0.0000

Data Index: 578306 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5879. Min Act: 0.0000

Data Index: 571300 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1786691 (The Pile)

Max Activating Token Index: 212

Text #6

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1225509 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5631. Min Act: -0.0000

Data Index: 564200 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5242. Min Act: -0.0000

Data Index: 303771 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1387905 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5224. Min Act: -0.0000

Data Index: 995629 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1894027 (The Pile)

Max Activating Token Index: 876

Text #12

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1734979 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1349804 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1574928 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5114. Min Act: 0.0002

Data Index: 226278 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1320708 (The Pile)

Max Activating Token Index: 683

Text #17

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1465932 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.4837. Min Act: -0.0000

Data Index: 685918 (The Pile)

Max Activating Token Index: 688

Text #19

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1426092 (The Pile)

Max Activating Token Index: 943