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

Dataset: The Pile

Neuron 3458 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: 0.2363. Min Range: -0.2363

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1806664 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2277. Min Act: -0.0000

Data Index: 615915 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1286366 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2101. Min Act: -0.0000

Data Index: 356931 (The Pile)

Max Activating Token Index: 551

Text #4

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1800716 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1397519 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1225424 (The Pile)

Max Activating Token Index: 777

Text #7

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1129101 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1633. Min Act: -0.0000

Data Index: 924442 (The Pile)

Max Activating Token Index: 850

Text #9

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1840. Min Act: -0.0000

Data Index: 40219 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2100. Min Act: -0.0000

Data Index: 179929 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1711. Min Act: -0.0000

Data Index: 261118 (The Pile)

Max Activating Token Index: 944

Text #12

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1241365 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1985017 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1703. Min Act: -0.0000

Data Index: 799477 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1730. Min Act: -0.0000

Data Index: 1065184 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1257613 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1728. Min Act: -0.0000

Data Index: 283185 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1549368 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1603. Min Act: -0.0000

Data Index: 499301 (The Pile)

Max Activating Token Index: 955