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

Dataset: The Pile

Neuron 2571 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6732. Min Range: -8.6732

Max Act: 8.6732. Min Act: -0.0000

Data Index: 1058384 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 8.6732. Min Range: -8.6732

Max Act: 8.0177. Min Act: -0.0000

Data Index: 1057328 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 8.6732. Min Range: -8.6732

Max Act: 7.9579. Min Act: -0.0000

Data Index: 379727 (The Pile)

Max Activating Token Index: 724

Text #3

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.6822. Min Act: -0.0000

Data Index: 1787299 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 8.6732. Min Range: -8.6732

Max Act: 7.2922. Min Act: -0.0000

Data Index: 1087612 (The Pile)

Max Activating Token Index: 653

Text #5

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.4214. Min Act: -0.0000

Data Index: 883393 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.1708. Min Act: -0.0000

Data Index: 520877 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.4157. Min Act: -0.0000

Data Index: 276466 (The Pile)

Max Activating Token Index: 546

Text #8

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.6283. Min Act: -0.0000

Data Index: 1681688 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.2768. Min Act: -0.0000

Data Index: 1512049 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.2080. Min Act: -0.0000

Data Index: 486970 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.6296. Min Act: -0.0000

Data Index: 1225484 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.1301. Min Act: -0.0000

Data Index: 158425 (The Pile)

Max Activating Token Index: 991

Text #13

Max Range: 8.6732. Min Range: -8.6732

Max Act: 5.7018. Min Act: -0.0000

Data Index: 465677 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 8.6732. Min Range: -8.6732

Max Act: 5.9691. Min Act: -0.0000

Data Index: 522723 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 8.6732. Min Range: -8.6732

Max Act: 5.9578. Min Act: -0.0000

Data Index: 913114 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.1719. Min Act: -0.0000

Data Index: 755299 (The Pile)

Max Activating Token Index: 596

Text #17

Max Range: 8.6732. Min Range: -8.6732

Max Act: 5.7263. Min Act: -0.0000

Data Index: 1362427 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 8.6732. Min Range: -8.6732

Max Act: 6.0977. Min Act: -0.0000

Data Index: 1394169 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 8.6732. Min Range: -8.6732

Max Act: 5.7902. Min Act: -0.0000

Data Index: 1551236 (The Pile)

Max Activating Token Index: 634