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

Dataset: The Pile

Neuron 2193 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.2991. Min Act: -0.0000

Data Index: 849461 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1009915 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1446489 (The Pile)

Max Activating Token Index: 166

Text #3

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1026453 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1638660 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8860. Min Act: 0.0000

Data Index: 1735333 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7161. Min Act: 0.0000

Data Index: 1202807 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.6840. Min Act: 0.0000

Data Index: 181331 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1775576 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7568. Min Act: -0.0000

Data Index: 899200 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7314. Min Act: -0.0000

Data Index: 27956 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.6853. Min Act: 0.0000

Data Index: 271333 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.6755. Min Act: -0.0000

Data Index: 660910 (The Pile)

Max Activating Token Index: 950

Text #13

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7126. Min Act: 0.0000

Data Index: 973733 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1324899 (The Pile)

Max Activating Token Index: 875

Text #15

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.5638. Min Act: -0.0000

Data Index: 319520 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7136. Min Act: -0.0000

Data Index: 479120 (The Pile)

Max Activating Token Index: 764

Text #17

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.6596. Min Act: 0.0000

Data Index: 1428346 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.6567. Min Act: 0.0000

Data Index: 130014 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7028. Min Act: 0.0000

Data Index: 937938 (The Pile)

Max Activating Token Index: 336