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

Dataset: The Pile

Neuron 4511 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: 7.2640. Min Range: -7.2640

Max Act: 7.2640. Min Act: -0.0000

Data Index: 78592 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 7.2640. Min Range: -7.2640

Max Act: 6.2803. Min Act: -0.0000

Data Index: 1800576 (The Pile)

Max Activating Token Index: 375

Text #2

Max Range: 7.2640. Min Range: -7.2640

Max Act: 6.5393. Min Act: -0.0000

Data Index: 1352824 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 7.2640. Min Range: -7.2640

Max Act: 6.3912. Min Act: -0.0000

Data Index: 388434 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 7.2640. Min Range: -7.2640

Max Act: 6.2318. Min Act: -0.0000

Data Index: 825164 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.7845. Min Act: -0.0000

Data Index: 881056 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 7.2640. Min Range: -7.2640

Max Act: 5.4544. Min Act: -0.0000

Data Index: 851787 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 7.2640. Min Range: -7.2640

Max Act: 5.1376. Min Act: -0.0000

Data Index: 7728 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 7.2640. Min Range: -7.2640

Max Act: 5.1495. Min Act: -0.0000

Data Index: 1890881 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.4045. Min Act: -0.0000

Data Index: 1245508 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.8364. Min Act: -0.0000

Data Index: 1009296 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.0934. Min Act: -0.0001

Data Index: 1585475 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.7507. Min Act: -0.0000

Data Index: 1478087 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.4705. Min Act: -0.0000

Data Index: 1064750 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.8921. Min Act: -0.0000

Data Index: 354194 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.6715. Min Act: -0.0000

Data Index: 1243693 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.7729. Min Act: -0.0000

Data Index: 206084 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 7.2640. Min Range: -7.2640

Max Act: 4.6189. Min Act: -0.0001

Data Index: 995723 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 7.2640. Min Range: -7.2640

Max Act: 3.8573. Min Act: -0.0000

Data Index: 1017324 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 7.2640. Min Range: -7.2640

Max Act: 5.3578. Min Act: -0.0000

Data Index: 350485 (The Pile)

Max Activating Token Index: 742