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

Dataset: The Pile

Neuron 2720 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: 1.7545. Min Range: -1.7545

Max Act: 1.7545. Min Act: 0.0000

Data Index: 1725408 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.6842. Min Act: -0.0000

Data Index: 985614 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.6098. Min Act: -0.0000

Data Index: 1277595 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.6921. Min Act: -0.0000

Data Index: 1645926 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.5863. Min Act: -0.0000

Data Index: 1679107 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.5614. Min Act: -0.0000

Data Index: 1356829 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.5661. Min Act: -0.0000

Data Index: 1023931 (The Pile)

Max Activating Token Index: 806

Text #7

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1090095 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4596. Min Act: -0.0000

Data Index: 1767121 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4531. Min Act: -0.0000

Data Index: 682527 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4254. Min Act: -0.0000

Data Index: 390230 (The Pile)

Max Activating Token Index: 20

Text #11

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4433. Min Act: -0.0000

Data Index: 1167224 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.3473. Min Act: -0.0000

Data Index: 129431 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4012. Min Act: -0.0000

Data Index: 410591 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1147926 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.4036. Min Act: -0.0000

Data Index: 1841761 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1396951 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1754153 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1263679 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 1.7545. Min Range: -1.7545

Max Act: 1.3888. Min Act: -0.0000

Data Index: 954492 (The Pile)

Max Activating Token Index: 68