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

Dataset: The Pile

Neuron 2810 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0560. Min Act: -0.0000

Data Index: 553100 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0708. Min Act: -0.0000

Data Index: 620645 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0638. Min Act: -0.0000

Data Index: 210763 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9927. Min Act: -0.0000

Data Index: 817399 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0392. Min Act: -0.0000

Data Index: 322555 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9201. Min Act: -0.0000

Data Index: 515369 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9452. Min Act: -0.0000

Data Index: 923927 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9451. Min Act: -0.0000

Data Index: 913394 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9277. Min Act: -0.0000

Data Index: 429658 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1891250 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 1.0708. Min Range: -1.0708

Max Act: 1.0212. Min Act: -0.0001

Data Index: 883462 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1021669 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9321. Min Act: -0.0000

Data Index: 724381 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.9355. Min Act: -0.0000

Data Index: 153253 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1727631 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1913249 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1054473 (The Pile)

Max Activating Token Index: 910

Text #17

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8713. Min Act: -0.0000

Data Index: 855404 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1727190 (The Pile)

Max Activating Token Index: 620

Text #19

Max Range: 1.0708. Min Range: -1.0708

Max Act: 0.8530. Min Act: -0.0000

Data Index: 805782 (The Pile)

Max Activating Token Index: 251