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

Dataset: The Pile

Neuron 1590 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0412. Min Range: -1.0412

Max Act: 1.0412. Min Act: -0.0000

Data Index: 283558 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1717688 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.9355. Min Act: -0.0000

Data Index: 489230 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1559264 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8698. Min Act: -0.0000

Data Index: 235505 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8876. Min Act: -0.0000

Data Index: 72093 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.9894. Min Act: -0.0000

Data Index: 687225 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1929648 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1667875 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8741. Min Act: -0.0000

Data Index: 545992 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1828248 (The Pile)

Max Activating Token Index: 169

Text #11

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8662. Min Act: -0.0000

Data Index: 921556 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1759253 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7947. Min Act: -0.0000

Data Index: 832823 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1617191 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1073201 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1756757 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1093182 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1757784 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1837761 (The Pile)

Max Activating Token Index: 875