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

Dataset: The Pile

Neuron 1846 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: 0.3672. Min Range: -0.3672

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1815870 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3277. Min Act: -0.0000

Data Index: 68345 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3146. Min Act: -0.0000

Data Index: 259657 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1033151 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1867723 (The Pile)

Max Activating Token Index: 699

Text #5

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1619148 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3307. Min Act: -0.0000

Data Index: 608800 (The Pile)

Max Activating Token Index: 741

Text #7

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1730995 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2983. Min Act: -0.0000

Data Index: 769233 (The Pile)

Max Activating Token Index: 270

Text #9

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2966. Min Act: -0.0000

Data Index: 767137 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1265434 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1624918 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3032. Min Act: -0.0000

Data Index: 549994 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2862. Min Act: -0.0000

Data Index: 758559 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2862. Min Act: -0.0000

Data Index: 505703 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1566870 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2752. Min Act: -0.0000

Data Index: 114046 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1610593 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1493519 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2673. Min Act: -0.0000

Data Index: 810270 (The Pile)

Max Activating Token Index: 886