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

Dataset: The Pile

Neuron 2471 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1392341 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2831. Min Act: -0.0000

Data Index: 963789 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2447. Min Act: -0.0000

Data Index: 938508 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1993415 (The Pile)

Max Activating Token Index: 594

Text #4

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1821413 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2360. Min Act: -0.0000

Data Index: 703272 (The Pile)

Max Activating Token Index: 728

Text #6

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1855. Min Act: -0.0000

Data Index: 271246 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1858598 (The Pile)

Max Activating Token Index: 342

Text #8

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1016601 (The Pile)

Max Activating Token Index: 629

Text #9

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1874967 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1020787 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1908. Min Act: -0.0000

Data Index: 851966 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1046516 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1450122 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2151. Min Act: -0.0000

Data Index: 384123 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1629681 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1536680 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1725006 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1608990 (The Pile)

Max Activating Token Index: 749

Text #19

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1865. Min Act: -0.0000

Data Index: 300078 (The Pile)

Max Activating Token Index: 781