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

Dataset: The Pile

Neuron 4917 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: 0.1533. Min Range: -0.1533

Max Act: 0.1533. Min Act: -0.0000

Data Index: 22466 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1928948 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1151. Min Act: -0.0000

Data Index: 948152 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1036519 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1729798 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1074. Min Act: -0.0000

Data Index: 732202 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1058598 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0933. Min Act: -0.0000

Data Index: 596306 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1013. Min Act: -0.0000

Data Index: 775438 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1002. Min Act: -0.0000

Data Index: 132701 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0933. Min Act: -0.0000

Data Index: 977092 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1531235 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0904. Min Act: -0.0000

Data Index: 758805 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0927. Min Act: -0.0000

Data Index: 430990 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0850. Min Act: -0.0000

Data Index: 102141 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0922. Min Act: -0.0000

Data Index: 286638 (The Pile)

Max Activating Token Index: 692

Text #16

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0914. Min Act: -0.0000

Data Index: 914496 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1613467 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0913. Min Act: -0.0000

Data Index: 27928 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.0907. Min Act: -0.0000

Data Index: 22822 (The Pile)

Max Activating Token Index: 499