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

Dataset: The Pile

Neuron 560 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: 1.1730. Min Range: -1.1730

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1447903 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.1279. Min Act: -0.0000

Data Index: 560555 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1989417 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0634. Min Act: -0.0000

Data Index: 835385 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1183280 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1322305 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0316. Min Act: -0.0000

Data Index: 892568 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1803498 (The Pile)

Max Activating Token Index: 318

Text #8

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1685006 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0063. Min Act: -0.0000

Data Index: 513712 (The Pile)

Max Activating Token Index: 755

Text #10

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0039. Min Act: -0.0000

Data Index: 406674 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1418732 (The Pile)

Max Activating Token Index: 526

Text #12

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9847. Min Act: -0.0000

Data Index: 873556 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1288882 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1099099 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 1.1730. Min Range: -1.1730

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1490333 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1464415 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1614341 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9782. Min Act: -0.0000

Data Index: 220525 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 1.1730. Min Range: -1.1730

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1872141 (The Pile)

Max Activating Token Index: 532