Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2195 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1400163 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.4386. Min Act: -0.0000

Data Index: 584619 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1711766 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3974. Min Act: -0.0000

Data Index: 32085 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1929695 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3956. Min Act: -0.0000

Data Index: 336674 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.4087. Min Act: -0.0000

Data Index: 918369 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3603. Min Act: -0.0000

Data Index: 811719 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1241912 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3639. Min Act: -0.0000

Data Index: 400346 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3820. Min Act: -0.0000

Data Index: 926215 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1768394 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3804. Min Act: -0.0000

Data Index: 307310 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1016093 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3851. Min Act: -0.0000

Data Index: 395313 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1553790 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3811. Min Act: -0.0000

Data Index: 368621 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3705. Min Act: -0.0000

Data Index: 103739 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1931346 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1863423 (The Pile)

Max Activating Token Index: 27