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

Dataset: The Pile

Neuron 4761 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: 0.6798. Min Range: -0.6798

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1505964 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1127483 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1385627 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5844. Min Act: -0.0000

Data Index: 727328 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5599. Min Act: 0.0000

Data Index: 1223934 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5248. Min Act: -0.0000

Data Index: 647006 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5163. Min Act: -0.0000

Data Index: 633321 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5234. Min Act: -0.0000

Data Index: 768322 (The Pile)

Max Activating Token Index: 128

Text #8

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5226. Min Act: 0.0000

Data Index: 1423195 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1481124 (The Pile)

Max Activating Token Index: 571

Text #10

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4730. Min Act: 0.0000

Data Index: 1741195 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1664202 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4902. Min Act: -0.0000

Data Index: 674634 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1472958 (The Pile)

Max Activating Token Index: 885

Text #14

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4707. Min Act: 0.0001

Data Index: 62609 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1294015 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1606716 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4494. Min Act: -0.0000

Data Index: 865460 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1436984 (The Pile)

Max Activating Token Index: 416

Text #19

Max Range: 0.6798. Min Range: -0.6798

Max Act: 0.4559. Min Act: -0.0000

Data Index: 710183 (The Pile)

Max Activating Token Index: 556