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

Dataset: The Pile

Neuron 1698 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: 0.2324. Min Range: -0.2324

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1268476 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1504120 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1330336 (The Pile)

Max Activating Token Index: 886

Text #3

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.2038. Min Act: -0.0000

Data Index: 663001 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1779. Min Act: -0.0000

Data Index: 290677 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1782087 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1843. Min Act: -0.0000

Data Index: 590119 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1184570 (The Pile)

Max Activating Token Index: 917

Text #8

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1659000 (The Pile)

Max Activating Token Index: 986

Text #9

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1305882 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1703. Min Act: -0.0000

Data Index: 305158 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1056036 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1634. Min Act: -0.0000

Data Index: 66741 (The Pile)

Max Activating Token Index: 887

Text #13

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1989765 (The Pile)

Max Activating Token Index: 953

Text #14

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1675. Min Act: -0.0000

Data Index: 215888 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1540422 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1384496 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1647. Min Act: -0.0000

Data Index: 563708 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1184166 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1989895 (The Pile)

Max Activating Token Index: 888