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

Dataset: The Pile

Neuron 2300 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: 9.0757. Min Range: -9.0757

Max Act: 8.2302. Min Act: -0.0000

Data Index: 1267142 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.6298. Min Act: -0.0000

Data Index: 1036380 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.2058. Min Act: -0.0000

Data Index: 1690105 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 9.0757. Min Range: -9.0757

Max Act: 7.6130. Min Act: -0.0000

Data Index: 946113 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.8893. Min Act: -0.0000

Data Index: 127391 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 9.0757. Min Range: -9.0757

Max Act: 9.0757. Min Act: -0.0000

Data Index: 1321743 (The Pile)

Max Activating Token Index: 790

Text #6

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.9110. Min Act: -0.0000

Data Index: 1956948 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.4536. Min Act: -0.0000

Data Index: 1128249 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.2593. Min Act: -0.0000

Data Index: 257482 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.5684. Min Act: -0.0000

Data Index: 1788370 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.7395. Min Act: -0.0000

Data Index: 717553 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.6265. Min Act: -0.0000

Data Index: 719984 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.2936. Min Act: -0.0000

Data Index: 211630 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.0545. Min Act: -0.0000

Data Index: 1747897 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 9.0757. Min Range: -9.0757

Max Act: 7.9297. Min Act: -0.0000

Data Index: 1024905 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 9.0757. Min Range: -9.0757

Max Act: 7.7915. Min Act: -0.0000

Data Index: 1687542 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.2987. Min Act: -0.0000

Data Index: 1722858 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.2127. Min Act: -0.0000

Data Index: 1457654 (The Pile)

Max Activating Token Index: 624

Text #18

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.0220. Min Act: -0.0000

Data Index: 1150894 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 9.0757. Min Range: -9.0757

Max Act: 8.1845. Min Act: -0.0000

Data Index: 40660 (The Pile)

Max Activating Token Index: 895