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

Dataset: The Pile

Neuron 3222 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1867652 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0988. Min Act: -0.0000

Data Index: 759036 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0880. Min Act: -0.0000

Data Index: 167759 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1026770 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1436028 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0864. Min Act: -0.0000

Data Index: 357679 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1787815 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0883. Min Act: -0.0000

Data Index: 526676 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0749. Min Act: -0.0000

Data Index: 952414 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0889. Min Act: -0.0000

Data Index: 67509 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0853. Min Act: -0.0000

Data Index: 384297 (The Pile)

Max Activating Token Index: 642

Text #11

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0879. Min Act: -0.0000

Data Index: 365619 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0811. Min Act: -0.0000

Data Index: 522127 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1818816 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1032063 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1110898 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1774908 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0794. Min Act: -0.0000

Data Index: 512902 (The Pile)

Max Activating Token Index: 612

Text #18

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1070095 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0770. Min Act: -0.0000

Data Index: 487042 (The Pile)

Max Activating Token Index: 202