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

Dataset: The Pile

Neuron 2310 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: 0.8166. Min Range: -0.8166

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1738090 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1784419 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7528. Min Act: -0.0000

Data Index: 50829 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1675346 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7839. Min Act: -0.0000

Data Index: 998010 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6741. Min Act: -0.0000

Data Index: 456535 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7816. Min Act: -0.0000

Data Index: 352134 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.8149. Min Act: -0.0000

Data Index: 94996 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7311. Min Act: -0.0000

Data Index: 488581 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7246. Min Act: -0.0000

Data Index: 1383631 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7016. Min Act: -0.0000

Data Index: 979002 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7476. Min Act: -0.0001

Data Index: 604427 (The Pile)

Max Activating Token Index: 720

Text #12

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7403. Min Act: -0.0000

Data Index: 934870 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7415. Min Act: -0.0000

Data Index: 678239 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7342. Min Act: -0.0000

Data Index: 873952 (The Pile)

Max Activating Token Index: 963

Text #15

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7002. Min Act: -0.0000

Data Index: 392966 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.7474. Min Act: -0.0001

Data Index: 104947 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1086560 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1893004 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 0.8166. Min Range: -0.8166

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1885434 (The Pile)

Max Activating Token Index: 380