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

Dataset: The Pile

Neuron 1350 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: 0.2888. Min Range: -0.2888

Max Act: 0.2888. Min Act: -0.0000

Data Index: 438210 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2735. Min Act: -0.0000

Data Index: 139414 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2214. Min Act: -0.0000

Data Index: 504816 (The Pile)

Max Activating Token Index: 740

Text #3

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2252. Min Act: -0.0000

Data Index: 760637 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1246957 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1997. Min Act: -0.0000

Data Index: 410455 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1506819 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1508760 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1843. Min Act: -0.0000

Data Index: 63456 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1603883 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1112381 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1436734 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1772. Min Act: -0.0000

Data Index: 678437 (The Pile)

Max Activating Token Index: 801

Text #13

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1743. Min Act: -0.0000

Data Index: 21132 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1728. Min Act: -0.0000

Data Index: 388304 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1534. Min Act: -0.0000

Data Index: 332379 (The Pile)

Max Activating Token Index: 649

Text #16

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1854. Min Act: -0.0000

Data Index: 189849 (The Pile)

Max Activating Token Index: 918

Text #17

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1649759 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1786715 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1528. Min Act: -0.0000

Data Index: 299603 (The Pile)

Max Activating Token Index: 828