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

Dataset: The Pile

Neuron 3962 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1675802 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1239980 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1717988 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4856. Min Act: -0.0000

Data Index: 476416 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4846. Min Act: -0.0000

Data Index: 421606 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4973. Min Act: -0.0000

Data Index: 506155 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1057108 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4950. Min Act: -0.0000

Data Index: 571009 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1553710 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1270561 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4484. Min Act: -0.0000

Data Index: 186813 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1951661 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1321433 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4102. Min Act: -0.0000

Data Index: 785347 (The Pile)

Max Activating Token Index: 153

Text #14

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4683. Min Act: -0.0000

Data Index: 402161 (The Pile)

Max Activating Token Index: 760

Text #15

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4221. Min Act: -0.0000

Data Index: 634061 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1004122 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.3725. Min Act: -0.0000

Data Index: 164409 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1715219 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 0.6850. Min Range: -0.6850

Max Act: 0.3986. Min Act: -0.0000

Data Index: 840390 (The Pile)

Max Activating Token Index: 426