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

Dataset: The Pile

Neuron 4253 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: 0.2684. Min Range: -0.2684

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1814104 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2639. Min Act: -0.0000

Data Index: 96440 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1226578 (The Pile)

Max Activating Token Index: 448

Text #3

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1822516 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1725914 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1941737 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1226936 (The Pile)

Max Activating Token Index: 894

Text #7

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1872. Min Act: -0.0000

Data Index: 992328 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2118. Min Act: -0.0000

Data Index: 685009 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1508843 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1980. Min Act: -0.0000

Data Index: 547970 (The Pile)

Max Activating Token Index: 481

Text #11

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1690530 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1992451 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1170926 (The Pile)

Max Activating Token Index: 387

Text #14

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1850. Min Act: -0.0000

Data Index: 841172 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1915. Min Act: -0.0000

Data Index: 405917 (The Pile)

Max Activating Token Index: 732

Text #16

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1186726 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1106159 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1816. Min Act: -0.0000

Data Index: 655780 (The Pile)

Max Activating Token Index: 987

Text #19

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1877374 (The Pile)

Max Activating Token Index: 188