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

Dataset: The Pile

Neuron 3436 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: 0.3047. Min Range: -0.3047

Max Act: 0.3047. Min Act: -0.0000

Data Index: 52952 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1673913 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1117406 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2276. Min Act: -0.0000

Data Index: 1275509 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1905. Min Act: -0.0000

Data Index: 161370 (The Pile)

Max Activating Token Index: 155

Text #5

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2012. Min Act: -0.0000

Data Index: 94612 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2217. Min Act: -0.0000

Data Index: 49117 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1040059 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2099. Min Act: -0.0000

Data Index: 158444 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1015491 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2252. Min Act: -0.0000

Data Index: 720569 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1469. Min Act: -0.0000

Data Index: 135180 (The Pile)

Max Activating Token Index: 585

Text #12

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1958. Min Act: -0.0000

Data Index: 705035 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1103385 (The Pile)

Max Activating Token Index: 429

Text #14

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1911882 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2018. Min Act: -0.0000

Data Index: 906583 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1940754 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1767842 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1936. Min Act: -0.0000

Data Index: 386728 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1925. Min Act: -0.0000

Data Index: 737429 (The Pile)

Max Activating Token Index: 445