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

Dataset: The Pile

Neuron 4836 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0667. Min Range: -1.0667

Max Act: 1.0667. Min Act: -0.0000

Data Index: 572978 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7626. Min Act: -0.0000

Data Index: 856403 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6431. Min Act: -0.0000

Data Index: 129094 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.5557. Min Act: -0.0000

Data Index: 155356 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1540447 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1940870 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1648412 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4550. Min Act: -0.0000

Data Index: 194557 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1967714 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4716. Min Act: -0.0000

Data Index: 865465 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4434. Min Act: -0.0000

Data Index: 648657 (The Pile)

Max Activating Token Index: 862

Text #11

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4766. Min Act: -0.0000

Data Index: 981732 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1583410 (The Pile)

Max Activating Token Index: 693

Text #13

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4625. Min Act: -0.0000

Data Index: 409546 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1097486 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1347659 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4251. Min Act: -0.0000

Data Index: 604221 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4771. Min Act: -0.0000

Data Index: 365129 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1097221 (The Pile)

Max Activating Token Index: 960

Text #19

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1630434 (The Pile)

Max Activating Token Index: 598