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

Dataset: The Pile

Neuron 623 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1381195 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1717804 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.1324. Min Act: -0.0000

Data Index: 281155 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0587. Min Act: -0.0000

Data Index: 530126 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1232322 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9603. Min Act: -0.0000

Data Index: 562072 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1955231 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1116359 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0375. Min Act: -0.0000

Data Index: 404620 (The Pile)

Max Activating Token Index: 467

Text #9

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1295824 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0462. Min Act: -0.0000

Data Index: 625152 (The Pile)

Max Activating Token Index: 85

Text #11

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0133. Min Act: -0.0000

Data Index: 910771 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0095. Min Act: -0.0000

Data Index: 538629 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1854637 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9369. Min Act: -0.0000

Data Index: 925421 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1813401 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0226. Min Act: -0.0000

Data Index: 1397257 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9808. Min Act: -0.0000

Data Index: 115599 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9572. Min Act: -0.0000

Data Index: 892016 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9270. Min Act: -0.0000

Data Index: 627983 (The Pile)

Max Activating Token Index: 32