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

Dataset: The Pile

Neuron 2263 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: 3.7589. Min Range: -3.7589

Max Act: 3.6118. Min Act: -0.0000

Data Index: 171100 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.7316. Min Act: -0.0000

Data Index: 1125524 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.7589. Min Act: -0.0000

Data Index: 545861 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0315. Min Act: -0.0000

Data Index: 1501007 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9877. Min Act: -0.0000

Data Index: 913640 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0855. Min Act: -0.0000

Data Index: 1754300 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.8519. Min Act: -0.0000

Data Index: 1248783 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.7467. Min Act: -0.0000

Data Index: 156099 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.1545. Min Act: -0.0000

Data Index: 1530599 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.7210. Min Act: -0.0000

Data Index: 278065 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0928. Min Act: -0.0000

Data Index: 556153 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9444. Min Act: -0.0000

Data Index: 1977566 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0545. Min Act: -0.0000

Data Index: 453566 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.7939. Min Act: -0.0000

Data Index: 399032 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0108. Min Act: -0.0000

Data Index: 1403758 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0218. Min Act: -0.0000

Data Index: 1069510 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.7089. Min Act: -0.0000

Data Index: 936501 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.8159. Min Act: -0.0000

Data Index: 891350 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.6869. Min Act: -0.0000

Data Index: 1830639 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.6245. Min Act: -0.0000

Data Index: 1382716 (The Pile)

Max Activating Token Index: 726