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

Dataset: The Pile

Neuron 1638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.5432. Min Act: -0.0000

Data Index: 1927063 (The Pile)

Max Activating Token Index: 924

Text #1

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.2359. Min Act: -0.0000

Data Index: 518493 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.3009. Min Act: -0.0000

Data Index: 1989614 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1201377 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.4168. Min Act: -0.0000

Data Index: 584957 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.3712. Min Act: -0.0000

Data Index: 1524107 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.2827. Min Act: -0.0000

Data Index: 726819 (The Pile)

Max Activating Token Index: 660

Text #7

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1973015 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1010. Min Act: -0.0000

Data Index: 633923 (The Pile)

Max Activating Token Index: 266

Text #9

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1581. Min Act: -0.0000

Data Index: 663966 (The Pile)

Max Activating Token Index: 200

Text #10

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1799122 (The Pile)

Max Activating Token Index: 526

Text #11

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1516632 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1404. Min Act: -0.0000

Data Index: 586739 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9748. Min Act: -0.0000

Data Index: 169118 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0990. Min Act: -0.0000

Data Index: 1032488 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1404657 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9253. Min Act: -0.0000

Data Index: 633178 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 1.5432. Min Range: -1.5432

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1453377 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.1840. Min Act: -0.0000

Data Index: 729674 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 1.5432. Min Range: -1.5432

Max Act: 1.0699. Min Act: -0.0000

Data Index: 596621 (The Pile)

Max Activating Token Index: 89