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

Dataset: The Pile

Neuron 4437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.4506. Min Act: -0.0000

Data Index: 786106 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1168155 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3890. Min Act: -0.0000

Data Index: 625691 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1279 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3223. Min Act: -0.0000

Data Index: 475108 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1047732 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1449094 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3031. Min Act: -0.0000

Data Index: 147861 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2849. Min Act: -0.0000

Data Index: 907433 (The Pile)

Max Activating Token Index: 681

Text #9

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2765. Min Act: -0.0000

Data Index: 54772 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1127723 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2654. Min Act: -0.0000

Data Index: 522866 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2731. Min Act: -0.0000

Data Index: 584305 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1630668 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1790468 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2779. Min Act: -0.0000

Data Index: 31605 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2581. Min Act: -0.0000

Data Index: 180125 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1191049 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1204725 (The Pile)

Max Activating Token Index: 652

Text #19

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2551. Min Act: -0.0000

Data Index: 971133 (The Pile)

Max Activating Token Index: 951