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

Dataset: The Pile

Neuron 4100 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: 1.0631. Min Range: -1.0631

Max Act: 1.0553. Min Act: -0.0000

Data Index: 1723153 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0574. Min Act: -0.0000

Data Index: 848330 (The Pile)

Max Activating Token Index: 6

Text #2

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1607122 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0261. Min Act: -0.0000

Data Index: 394444 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0631. Min Act: -0.0000

Data Index: 854653 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1967416 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1672852 (The Pile)

Max Activating Token Index: 4

Text #7

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1613598 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9600. Min Act: -0.0000

Data Index: 579446 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9810. Min Act: -0.0000

Data Index: 50321 (The Pile)

Max Activating Token Index: 4

Text #10

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1647983 (The Pile)

Max Activating Token Index: 4

Text #11

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9732. Min Act: -0.0000

Data Index: 84476 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1348055 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1411514 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9244. Min Act: -0.0000

Data Index: 248406 (The Pile)

Max Activating Token Index: 746

Text #15

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9611. Min Act: -0.0000

Data Index: 196132 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1308446 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9441. Min Act: -0.0000

Data Index: 542766 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8903. Min Act: -0.0000

Data Index: 77847 (The Pile)

Max Activating Token Index: 11

Text #19

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9986. Min Act: -0.0000

Data Index: 957274 (The Pile)

Max Activating Token Index: 872