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

Dataset: The Pile

Neuron 2986 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1129889 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1286302 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2241. Min Act: -0.0000

Data Index: 503263 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2014. Min Act: -0.0000

Data Index: 133613 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1247444 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1427176 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2328. Min Act: -0.0000

Data Index: 790559 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1451034 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1688. Min Act: -0.0000

Data Index: 329384 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1191875 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1781. Min Act: -0.0000

Data Index: 980590 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1778. Min Act: -0.0000

Data Index: 736197 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1098913 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1795. Min Act: -0.0000

Data Index: 635868 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1610. Min Act: -0.0000

Data Index: 923910 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1793. Min Act: -0.0000

Data Index: 989701 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1764. Min Act: -0.0000

Data Index: 249870 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1055190 (The Pile)

Max Activating Token Index: 509

Text #18

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1722. Min Act: -0.0000

Data Index: 609649 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1553. Min Act: -0.0000

Data Index: 573564 (The Pile)

Max Activating Token Index: 578