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

Dataset: The Pile

Neuron 834 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: 0.2754. Min Range: -0.2754

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1703114 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1093205 (The Pile)

Max Activating Token Index: 973

Text #2

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1731665 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1529061 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2251. Min Act: -0.0000

Data Index: 626381 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2252. Min Act: -0.0000

Data Index: 865883 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2176. Min Act: -0.0000

Data Index: 340663 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1199024 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1036695 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2192. Min Act: -0.0000

Data Index: 615238 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2115. Min Act: -0.0000

Data Index: 405570 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1211648 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1252275 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2059. Min Act: -0.0000

Data Index: 573237 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2055. Min Act: -0.0000

Data Index: 372021 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1719043 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2073. Min Act: -0.0000

Data Index: 617380 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1946. Min Act: -0.0000

Data Index: 56664 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1415935 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2046. Min Act: -0.0001

Data Index: 4376 (The Pile)

Max Activating Token Index: 880