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

Dataset: The Pile

Neuron 4519 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1997. Min Range: -1.1997

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1266858 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 1.1997. Min Range: -1.1997

Max Act: 1.0108. Min Act: -0.0000

Data Index: 1629505 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1408118 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1777621 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8843. Min Act: 0.0000

Data Index: 57772 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.9312. Min Act: -0.0000

Data Index: 495078 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1069610 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1092469 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8376. Min Act: -0.0000

Data Index: 142102 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1706599 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7766. Min Act: -0.0000

Data Index: 304950 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7698. Min Act: -0.0000

Data Index: 894696 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8108. Min Act: 0.0000

Data Index: 785803 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1923116 (The Pile)

Max Activating Token Index: 739

Text #14

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8047. Min Act: -0.0000

Data Index: 387640 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1726642 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1796050 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7851. Min Act: 0.0000

Data Index: 1812086 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1091074 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 1.1997. Min Range: -1.1997

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1760541 (The Pile)

Max Activating Token Index: 803