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

Dataset: The Pile

Neuron 877 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: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0000

Data Index: 801329 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1233120 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1755. Min Act: -0.0000

Data Index: 586556 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1986611 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1604060 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1541. Min Act: -0.0000

Data Index: 81696 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1795429 (The Pile)

Max Activating Token Index: 804

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1607. Min Act: -0.0000

Data Index: 627314 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1379010 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1667. Min Act: -0.0000

Data Index: 276818 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1494. Min Act: -0.0000

Data Index: 522866 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1611775 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1125981 (The Pile)

Max Activating Token Index: 226

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1528. Min Act: -0.0000

Data Index: 732232 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1596068 (The Pile)

Max Activating Token Index: 199

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1508. Min Act: -0.0000

Data Index: 314817 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1144105 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1829187 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1636744 (The Pile)

Max Activating Token Index: 720

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1360272 (The Pile)

Max Activating Token Index: 850