Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 54 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4542. Min Act: -0.0000

Data Index: 811691 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4197. Min Act: -0.0000

Data Index: 870873 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1149669 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1099258 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3864. Min Act: -0.0000

Data Index: 586865 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1182463 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3777. Min Act: -0.0000

Data Index: 292488 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3549. Min Act: -0.0000

Data Index: 585517 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1265816 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1177872 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3619. Min Act: -0.0000

Data Index: 369195 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1569194 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3331. Min Act: -0.0000

Data Index: 303826 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1944887 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1051102 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1784829 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3096. Min Act: -0.0000

Data Index: 816570 (The Pile)

Max Activating Token Index: 758

Text #17

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1341228 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.2959. Min Act: -0.0000

Data Index: 468429 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1253959 (The Pile)

Max Activating Token Index: 239