Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7599. Min Act: -0.0000

Data Index: 660578 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1394641 (The Pile)

Max Activating Token Index: 870

Text #2

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1469072 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1985917 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1963794 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1928443 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.0451. Min Act: -0.0000

Data Index: 655783 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1362572 (The Pile)

Max Activating Token Index: 796

Text #8

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.1050. Min Act: -0.0000

Data Index: 765678 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1893100 (The Pile)

Max Activating Token Index: 165

Text #10

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.0390. Min Act: -0.0000

Data Index: 756203 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1351994 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 1.7599. Min Range: -1.7599

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1898941 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 1.7599. Min Range: -1.7599

Max Act: 0.9405. Min Act: -0.0000

Data Index: 852494 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 1.7599. Min Range: -1.7599

Max Act: 0.8899. Min Act: -0.0000

Data Index: 317732 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1709213 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 1.7599. Min Range: -1.7599

Max Act: 0.8741. Min Act: -0.0000

Data Index: 888699 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 1.7599. Min Range: -1.7599

Max Act: 0.9083. Min Act: -0.0000

Data Index: 132684 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 1.7599. Min Range: -1.7599

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1406502 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 1.7599. Min Range: -1.7599

Max Act: 0.9353. Min Act: -0.0000

Data Index: 636451 (The Pile)

Max Activating Token Index: 741