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

Dataset: The Pile

Neuron 2074 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1808825 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1617756 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0860. Min Act: -0.0000

Data Index: 175453 (The Pile)

Max Activating Token Index: 886

Text #3

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1032848 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1827868 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0941. Min Act: -0.0000

Data Index: 58937 (The Pile)

Max Activating Token Index: 859

Text #6

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0895. Min Act: -0.0001

Data Index: 956258 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0828. Min Act: -0.0000

Data Index: 698602 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1440737 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1172452 (The Pile)

Max Activating Token Index: 387

Text #10

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0869. Min Act: -0.0001

Data Index: 731791 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0837. Min Act: -0.0000

Data Index: 827012 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1117329 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0772. Min Act: -0.0000

Data Index: 599980 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1754664 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1476307 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1989253 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0852. Min Act: -0.0000

Data Index: 342935 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1079617 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1419290 (The Pile)

Max Activating Token Index: 862