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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2790 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1076526 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.6214. Min Act: -0.0000

Data Index: 102391 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5376. Min Act: -0.0000

Data Index: 803296 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4919. Min Act: -0.0000

Data Index: 177679 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4941. Min Act: -0.0000

Data Index: 692855 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5068. Min Act: -0.0000

Data Index: 49632 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4908. Min Act: -0.0000

Data Index: 214237 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5037. Min Act: -0.0000

Data Index: 176063 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4715. Min Act: -0.0000

Data Index: 180930 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4595. Min Act: 0.0000

Data Index: 1175348 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4719. Min Act: -0.0000

Data Index: 90119 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4541. Min Act: -0.0000

Data Index: 424922 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1328315 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4785. Min Act: 0.0000

Data Index: 450112 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4620. Min Act: -0.0000

Data Index: 614029 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1017498 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4669. Min Act: -0.0000

Data Index: 162989 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4515. Min Act: -0.0000

Data Index: 618773 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4626. Min Act: -0.0000

Data Index: 578982 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1332142 (C4 (Web Text))

Max Activating Token Index: 260