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

Dataset: The Pile

Neuron 4443 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: 0.2418. Min Range: -0.2418

Max Act: 0.2418. Min Act: -0.0000

Data Index: 760365 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1851. Min Act: -0.0000

Data Index: 657139 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1228622 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1960. Min Act: -0.0000

Data Index: 688436 (The Pile)

Max Activating Token Index: 84

Text #4

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.2005. Min Act: -0.0000

Data Index: 725837 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.2144. Min Act: -0.0000

Data Index: 618393 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.2263. Min Act: -0.0000

Data Index: 858456 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1904. Min Act: -0.0000

Data Index: 335193 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1625950 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1079835 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1126200 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.2044. Min Act: -0.0000

Data Index: 775896 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1980077 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1058350 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1597. Min Act: -0.0000

Data Index: 93663 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1148518 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1128842 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1770341 (The Pile)

Max Activating Token Index: 877

Text #18

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1640307 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 0.2418. Min Range: -0.2418

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1084414 (The Pile)

Max Activating Token Index: 674