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

Dataset: The Pile

Neuron 460 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: 0.2196. Min Range: -0.2196

Max Act: 0.2196. Min Act: -0.0000

Data Index: 874486 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1991645 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1786689 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1992. Min Act: -0.0000

Data Index: 731428 (The Pile)

Max Activating Token Index: 690

Text #4

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1848559 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1756941 (The Pile)

Max Activating Token Index: 844

Text #6

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1826. Min Act: -0.0000

Data Index: 778557 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1811. Min Act: -0.0000

Data Index: 880369 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1758686 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1844. Min Act: -0.0000

Data Index: 767885 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1311223 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1859. Min Act: -0.0000

Data Index: 318472 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1239181 (The Pile)

Max Activating Token Index: 558

Text #13

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1741. Min Act: -0.0000

Data Index: 178894 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1602. Min Act: -0.0000

Data Index: 647917 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1461654 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1362826 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1589. Min Act: -0.0000

Data Index: 273600 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1071024 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1568. Min Act: -0.0000

Data Index: 635323 (The Pile)

Max Activating Token Index: 118