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

Dataset: The Pile

Neuron 830 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: 0.2623. Min Range: -0.2623

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1671792 (The Pile)

Max Activating Token Index: 695

Text #1

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1543081 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2236. Min Act: -0.0000

Data Index: 211066 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1999056 (The Pile)

Max Activating Token Index: 930

Text #4

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1750232 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2118. Min Act: -0.0000

Data Index: 65314 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1974. Min Act: -0.0000

Data Index: 573208 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1415085 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1825. Min Act: -0.0000

Data Index: 427308 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1328285 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.2008. Min Act: -0.0000

Data Index: 614218 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1809. Min Act: -0.0000

Data Index: 517801 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1754. Min Act: -0.0000

Data Index: 132971 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1316674 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1170761 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1239121 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1882. Min Act: -0.0000

Data Index: 717134 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1871. Min Act: -0.0000

Data Index: 571322 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1750. Min Act: -0.0000

Data Index: 838244 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 0.2623. Min Range: -0.2623

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1318111 (The Pile)

Max Activating Token Index: 333