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

Dataset: The Pile

Neuron 563 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: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1433283 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0745. Min Act: -0.0000

Data Index: 501847 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0691. Min Act: -0.0000

Data Index: 796699 (The Pile)

Max Activating Token Index: 716

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0625. Min Act: -0.0000

Data Index: 491957 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0608. Min Act: -0.0000

Data Index: 29023 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1782538 (The Pile)

Max Activating Token Index: 390

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1051248 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1345211 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1333958 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1362184 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0602. Min Act: -0.0000

Data Index: 793109 (The Pile)

Max Activating Token Index: 617

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1531099 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1426690 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0524. Min Act: -0.0000

Data Index: 601590 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1455620 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0566. Min Act: -0.0000

Data Index: 861423 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0585. Min Act: -0.0000

Data Index: 311319 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1904791 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0543. Min Act: -0.0000

Data Index: 275355 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1414092 (The Pile)

Max Activating Token Index: 310