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

Dataset: The Pile

Neuron 3693 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: 8.1427. Min Range: -8.1427

Max Act: 8.1427. Min Act: -0.0000

Data Index: 561503 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 8.1427. Min Range: -8.1427

Max Act: 6.7396. Min Act: -0.0000

Data Index: 50659 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 8.1427. Min Range: -8.1427

Max Act: 6.9384. Min Act: -0.0000

Data Index: 630623 (The Pile)

Max Activating Token Index: 99

Text #3

Max Range: 8.1427. Min Range: -8.1427

Max Act: 6.6645. Min Act: -0.0000

Data Index: 1553589 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 8.1427. Min Range: -8.1427

Max Act: 6.5392. Min Act: -0.0000

Data Index: 236589 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 8.1427. Min Range: -8.1427

Max Act: 6.2119. Min Act: -0.0000

Data Index: 717585 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 8.1427. Min Range: -8.1427

Max Act: 6.4552. Min Act: -0.0000

Data Index: 593596 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.8858. Min Act: -0.0000

Data Index: 1229789 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.9161. Min Act: -0.0000

Data Index: 53006 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 8.1427. Min Range: -8.1427

Max Act: 6.3967. Min Act: -0.0000

Data Index: 439528 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 8.1427. Min Range: -8.1427

Max Act: 6.1752. Min Act: -0.0000

Data Index: 1996669 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.8090. Min Act: -0.0000

Data Index: 513313 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.5116. Min Act: -0.0000

Data Index: 981914 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.6378. Min Act: -0.0000

Data Index: 276598 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.7773. Min Act: -0.0000

Data Index: 1467211 (The Pile)

Max Activating Token Index: 486

Text #15

Max Range: 8.1427. Min Range: -8.1427

Max Act: 6.1067. Min Act: -0.0000

Data Index: 215962 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.5652. Min Act: -0.0000

Data Index: 1753008 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.8893. Min Act: -0.0000

Data Index: 1328405 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.4679. Min Act: -0.0000

Data Index: 666175 (The Pile)

Max Activating Token Index: 201

Text #19

Max Range: 8.1427. Min Range: -8.1427

Max Act: 5.8384. Min Act: -0.0000

Data Index: 787220 (The Pile)

Max Activating Token Index: 387