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

Dataset: The Pile

Neuron 2586 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: 0.9590. Min Range: -0.9590

Max Act: 0.9590. Min Act: -0.0000

Data Index: 828628 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1143415 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8647. Min Act: -0.0000

Data Index: 319924 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1742908 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1043303 (The Pile)

Max Activating Token Index: 79

Text #5

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1025702 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8051. Min Act: -0.0000

Data Index: 658064 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8100. Min Act: -0.0000

Data Index: 94726 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1836509 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7533. Min Act: -0.0000

Data Index: 702859 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1832332 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1730136 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1703622 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1320084 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7096. Min Act: -0.0000

Data Index: 838124 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7060. Min Act: -0.0000

Data Index: 605195 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.6838. Min Act: -0.0000

Data Index: 354817 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1392891 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1771718 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.6233. Min Act: -0.0000

Data Index: 85738 (The Pile)

Max Activating Token Index: 960