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

Dataset: The Pile

Neuron 126 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: 3.2649. Min Range: -3.2649

Max Act: 3.2649. Min Act: -0.0000

Data Index: 1771341 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.8603. Min Act: -0.0000

Data Index: 1733604 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.0639. Min Act: -0.0000

Data Index: 1020243 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1845. Min Act: -0.0000

Data Index: 8146 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1392. Min Act: -0.0000

Data Index: 1252048 (The Pile)

Max Activating Token Index: 859

Text #5

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.8589. Min Act: -0.0000

Data Index: 237344 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.4570. Min Act: -0.0000

Data Index: 1538628 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.4613. Min Act: -0.0000

Data Index: 360740 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 3.2649. Min Range: -3.2649

Max Act: 3.1325. Min Act: -0.0000

Data Index: 1613726 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.9426. Min Act: -0.0000

Data Index: 611154 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.9464. Min Act: -0.0000

Data Index: 631684 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.9111. Min Act: -0.0000

Data Index: 74671 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.7445. Min Act: -0.0000

Data Index: 1008821 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.7040. Min Act: -0.0000

Data Index: 1164633 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.7219. Min Act: -0.0000

Data Index: 1022990 (The Pile)

Max Activating Token Index: 728

Text #15

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.4007. Min Act: -0.0000

Data Index: 360992 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.6503. Min Act: -0.0000

Data Index: 281157 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.3791. Min Act: -0.0000

Data Index: 516336 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.6618. Min Act: -0.0000

Data Index: 175657 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 3.2649. Min Range: -3.2649

Max Act: 2.4986. Min Act: -0.0000

Data Index: 1080838 (The Pile)

Max Activating Token Index: 712