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

Dataset: The Pile

Neuron 4412 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: 0.2232. Min Range: -0.2232

Max Act: 0.2009. Min Act: -0.0000

Data Index: 165263 (The Pile)

Max Activating Token Index: 550

Text #1

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1891. Min Act: -0.0000

Data Index: 495233 (The Pile)

Max Activating Token Index: 88

Text #2

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1194519 (The Pile)

Max Activating Token Index: 90

Text #3

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1149541 (The Pile)

Max Activating Token Index: 280

Text #4

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1731433 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1237250 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1251445 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1160517 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1812. Min Act: -0.0000

Data Index: 723768 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1756. Min Act: -0.0000

Data Index: 470803 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1206353 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1279 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1288366 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1578. Min Act: -0.0000

Data Index: 928293 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1038256 (The Pile)

Max Activating Token Index: 563

Text #15

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1415857 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1616832 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1545845 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1568757 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 0.2232. Min Range: -0.2232

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1131495 (The Pile)

Max Activating Token Index: 183