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

Dataset: The Pile

Neuron 4290 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1481180 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1640931 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.4232. Min Act: -0.0000

Data Index: 491278 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1064979 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.4131. Min Act: -0.0000

Data Index: 107642 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1349907 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.4092. Min Act: -0.0000

Data Index: 996647 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1217877 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3685. Min Act: -0.0000

Data Index: 436447 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1636511 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3606. Min Act: -0.0000

Data Index: 659582 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3834. Min Act: -0.0000

Data Index: 866398 (The Pile)

Max Activating Token Index: 732

Text #12

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3909. Min Act: -0.0000

Data Index: 561472 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1256094 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1336428 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.4007. Min Act: -0.0000

Data Index: 401157 (The Pile)

Max Activating Token Index: 95

Text #16

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1032282 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3688. Min Act: -0.0000

Data Index: 319135 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1590888 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 0.4882. Min Range: -0.4882

Max Act: 0.3743. Min Act: -0.0000

Data Index: 200076 (The Pile)

Max Activating Token Index: 989