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

Dataset: The Pile

Neuron 868 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: 1.0882. Min Range: -1.0882

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1889243 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.9791. Min Act: -0.0000

Data Index: 763701 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8972. Min Act: -0.0000

Data Index: 669388 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8794. Min Act: -0.0000

Data Index: 291809 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8376. Min Act: -0.0000

Data Index: 6555 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1493927 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.7521. Min Act: -0.0000

Data Index: 32758 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1619635 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8478. Min Act: -0.0000

Data Index: 841185 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8814. Min Act: -0.0000

Data Index: 730591 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8755. Min Act: -0.0000

Data Index: 614687 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1680102 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8039. Min Act: -0.0000

Data Index: 165423 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1597712 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1108305 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.8351. Min Act: -0.0000

Data Index: 240313 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1145694 (The Pile)

Max Activating Token Index: 822

Text #17

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.7737. Min Act: -0.0000

Data Index: 957752 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1400369 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 1.0882. Min Range: -1.0882

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1711743 (The Pile)

Max Activating Token Index: 931