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

Dataset: The Pile

Neuron 3240 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: 0.6615. Min Range: -0.6615

Max Act: 0.6615. Min Act: -0.0000

Data Index: 582931 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6534. Min Act: -0.0000

Data Index: 218662 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1205403 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1910108 (The Pile)

Max Activating Token Index: 816

Text #4

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1711526 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1059220 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1383902 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1728675 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5815. Min Act: -0.0000

Data Index: 696684 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5859. Min Act: -0.0000

Data Index: 150571 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6028. Min Act: -0.0000

Data Index: 701472 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5824. Min Act: -0.0000

Data Index: 306423 (The Pile)

Max Activating Token Index: 1005

Text #12

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1949970 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1853900 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1922490 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5906. Min Act: -0.0000

Data Index: 724110 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5421. Min Act: -0.0000

Data Index: 320178 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.6016. Min Act: -0.0000

Data Index: 941435 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1120084 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 0.6615. Min Range: -0.6615

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1282867 (The Pile)

Max Activating Token Index: 516