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

Dataset: The Pile

Neuron 1031 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: 0.7055. Min Range: -0.7055

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1777828 (The Pile)

Max Activating Token Index: 27

Text #1

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.7055. Min Act: -0.0000

Data Index: 291047 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6552. Min Act: 0.0000

Data Index: 1347055 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5735. Min Act: -0.0000

Data Index: 247632 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6359. Min Act: -0.0000

Data Index: 420670 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1253795 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1457651 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6019. Min Act: -0.0000

Data Index: 116698 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1032147 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5785. Min Act: 0.0000

Data Index: 1587845 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5711. Min Act: 0.0000

Data Index: 586569 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6064. Min Act: 0.0000

Data Index: 181162 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5719. Min Act: 0.0000

Data Index: 1199834 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1761608 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5554. Min Act: -0.0000

Data Index: 509403 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5667. Min Act: -0.0000

Data Index: 656287 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5638. Min Act: 0.0000

Data Index: 1436778 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1685299 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5622. Min Act: -0.0000

Data Index: 205534 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5801. Min Act: 0.0000

Data Index: 484127 (The Pile)

Max Activating Token Index: 17