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

Dataset: The Pile

Neuron 3528 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: 1.6706. Min Range: -1.6706

Max Act: 1.6706. Min Act: -0.0000

Data Index: 780058 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.3998. Min Act: -0.0000

Data Index: 750139 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.4959. Min Act: -0.0000

Data Index: 1712559 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.2753. Min Act: -0.0000

Data Index: 989343 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1694137 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.4144. Min Act: -0.0000

Data Index: 879030 (The Pile)

Max Activating Token Index: 844

Text #6

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1132080 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.2871. Min Act: -0.0000

Data Index: 459501 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.1310. Min Act: -0.0000

Data Index: 445459 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.2245. Min Act: -0.0000

Data Index: 239293 (The Pile)

Max Activating Token Index: 996

Text #10

Max Range: 1.6706. Min Range: -1.6706

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1697641 (The Pile)

Max Activating Token Index: 646

Text #11

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.2687. Min Act: -0.0000

Data Index: 591088 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.1548. Min Act: -0.0000

Data Index: 1894506 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.3072. Min Act: -0.0000

Data Index: 1008106 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.1519. Min Act: -0.0000

Data Index: 708114 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.1486. Min Act: -0.0000

Data Index: 135545 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1325298 (The Pile)

Max Activating Token Index: 331

Text #17

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1334554 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.1232. Min Act: -0.0000

Data Index: 561558 (The Pile)

Max Activating Token Index: 866

Text #19

Max Range: 1.6706. Min Range: -1.6706

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1010983 (The Pile)

Max Activating Token Index: 980