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

Dataset: The Pile

Neuron 2726 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: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1667669 (The Pile)

Max Activating Token Index: 543

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1694549 (The Pile)

Max Activating Token Index: 101

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0617. Min Act: -0.0000

Data Index: 35055 (The Pile)

Max Activating Token Index: 340

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0626. Min Act: -0.0000

Data Index: 436913 (The Pile)

Max Activating Token Index: 506

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0592. Min Act: -0.0000

Data Index: 601168 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0559. Min Act: -0.0000

Data Index: 72118 (The Pile)

Max Activating Token Index: 75

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0571. Min Act: -0.0000

Data Index: 386605 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0555. Min Act: -0.0000

Data Index: 475930 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0615. Min Act: -0.0000

Data Index: 25133 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1798070 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1956829 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0547. Min Act: -0.0000

Data Index: 1510645 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0572. Min Act: -0.0000

Data Index: 708087 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1567989 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0570. Min Act: -0.0000

Data Index: 847136 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0552. Min Act: -0.0000

Data Index: 109496 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0543. Min Act: -0.0000

Data Index: 4992 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1908002 (The Pile)

Max Activating Token Index: 168

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0570. Min Act: -0.0000

Data Index: 49737 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1045571 (The Pile)

Max Activating Token Index: 751