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

Dataset: The Pile

Neuron 1055 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: 0.2882. Min Range: -0.2882

Max Act: 0.2777. Min Act: -0.0000

Data Index: 454394 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2823. Min Act: -0.0000

Data Index: 416351 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1478484 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2882. Min Act: -0.0000

Data Index: 803281 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1211631 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1020850 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1796672 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2026. Min Act: -0.0000

Data Index: 851067 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1465514 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1873. Min Act: -0.0000

Data Index: 827550 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1842939 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1509365 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2099. Min Act: -0.0000

Data Index: 258069 (The Pile)

Max Activating Token Index: 207

Text #13

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1199082 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1224244 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1903. Min Act: -0.0000

Data Index: 643511 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1840. Min Act: -0.0000

Data Index: 171305 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1522. Min Act: -0.0000

Data Index: 723333 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1552. Min Act: -0.0000

Data Index: 378094 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1618579 (The Pile)

Max Activating Token Index: 416