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

Dataset: The Pile

Neuron 482 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1903900 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1556803 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6465. Min Act: -0.0000

Data Index: 220611 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1991898 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1407491 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5853. Min Act: -0.0000

Data Index: 950601 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1359058 (The Pile)

Max Activating Token Index: 817

Text #7

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5929. Min Act: -0.0000

Data Index: 364380 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1360267 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1408717 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1097811 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5653. Min Act: -0.0000

Data Index: 419369 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6003. Min Act: -0.0000

Data Index: 498517 (The Pile)

Max Activating Token Index: 881

Text #13

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1116715 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1414148 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6075. Min Act: -0.0000

Data Index: 355034 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1555724 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1753363 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.6245. Min Act: -0.0000

Data Index: 865450 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 0.7000. Min Range: -0.7000

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1110988 (The Pile)

Max Activating Token Index: 624