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

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

Neuron 2600 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: 0.7073. Min Range: -0.7073

Max Act: 0.7058. Min Act: -0.0000

Data Index: 441383 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6721. Min Act: 0.0000

Data Index: 808662 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1283807 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6517. Min Act: -0.0000

Data Index: 839265 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6625. Min Act: -0.0000

Data Index: 422060 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6528. Min Act: -0.0000

Data Index: 149527 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6570. Min Act: -0.0000

Data Index: 74444 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6031. Min Act: 0.0000

Data Index: 88424 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6021. Min Act: -0.0000

Data Index: 440232 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5780. Min Act: -0.0000

Data Index: 70270 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5790. Min Act: -0.0000

Data Index: 40828 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5785. Min Act: -0.0000

Data Index: 91723 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5473. Min Act: -0.0000

Data Index: 507054 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1161245 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5837. Min Act: -0.0000

Data Index: 612712 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5429. Min Act: -0.0000

Data Index: 991484 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.6016. Min Act: -0.0000

Data Index: 354039 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5378. Min Act: -0.0000

Data Index: 220970 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5245. Min Act: -0.0000

Data Index: 876140 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.7073. Min Range: -0.7073

Max Act: 0.5551. Min Act: 0.0000

Data Index: 124773 (C4 (Web Text))

Max Activating Token Index: 806