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

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

Neuron 3009 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.4222. Min Act: -0.0002

Data Index: 1146737 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.4699. Min Act: -0.0002

Data Index: 234448 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3987. Min Act: -0.0002

Data Index: 1296854 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3667. Min Act: -0.0002

Data Index: 368381 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3778. Min Act: -0.0002

Data Index: 721675 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3978. Min Act: -0.0002

Data Index: 242300 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.4190. Min Act: -0.0002

Data Index: 44877 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3934. Min Act: -0.0002

Data Index: 679653 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3501. Min Act: -0.0002

Data Index: 1219982 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3039. Min Act: -0.0002

Data Index: 128576 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3537. Min Act: -0.0002

Data Index: 978785 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3736. Min Act: -0.0002

Data Index: 892886 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3723. Min Act: -0.0002

Data Index: 57350 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3732. Min Act: -0.0002

Data Index: 430102 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3894. Min Act: -0.0002

Data Index: 750495 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3759. Min Act: -0.0002

Data Index: 732234 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3594. Min Act: -0.0002

Data Index: 406759 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3563. Min Act: -0.0002

Data Index: 790221 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3223. Min Act: -0.0002

Data Index: 543550 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.2993. Min Act: -0.0002

Data Index: 909361 (C4 (Web Text))

Max Activating Token Index: 287