Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2668 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1218816 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.5251. Min Act: -0.0000

Data Index: 813135 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.5116. Min Act: -0.0000

Data Index: 229580 (The Pile)

Max Activating Token Index: 566

Text #3

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4785. Min Act: -0.0000

Data Index: 177223 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4617. Min Act: -0.0000

Data Index: 270694 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1201834 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1445700 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4037. Min Act: -0.0000

Data Index: 629946 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1609837 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4066. Min Act: -0.0000

Data Index: 512734 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4024. Min Act: -0.0000

Data Index: 806899 (The Pile)

Max Activating Token Index: 743

Text #11

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1123028 (The Pile)

Max Activating Token Index: 728

Text #12

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3824. Min Act: -0.0000

Data Index: 321333 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3656. Min Act: -0.0000

Data Index: 627001 (The Pile)

Max Activating Token Index: 19

Text #14

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3907. Min Act: -0.0000

Data Index: 692631 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3746. Min Act: -0.0000

Data Index: 374071 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1048888 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1808889 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1754862 (The Pile)

Max Activating Token Index: 896

Text #19

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3603. Min Act: -0.0000

Data Index: 282485 (The Pile)

Max Activating Token Index: 103