Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1777 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1098. Min Act: -0.0006

Data Index: 928333 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0916. Min Act: -0.0006

Data Index: 8712 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0839. Min Act: -0.0006

Data Index: 476410 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0866. Min Act: -0.0006

Data Index: 555749 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0857. Min Act: -0.0006

Data Index: 583825 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0890. Min Act: -0.0006

Data Index: 818019 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0807. Min Act: -0.0006

Data Index: 740722 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0838. Min Act: -0.0006

Data Index: 125197 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0775. Min Act: -0.0006

Data Index: 428381 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0802. Min Act: -0.0006

Data Index: 774938 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0772. Min Act: -0.0006

Data Index: 631770 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0797. Min Act: -0.0006

Data Index: 963598 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0797. Min Act: -0.0006

Data Index: 718175 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0796. Min Act: -0.0006

Data Index: 789541 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0794. Min Act: -0.0006

Data Index: 24750 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0789. Min Act: -0.0006

Data Index: 159164 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0753. Min Act: -0.0006

Data Index: 1009483 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0739. Min Act: -0.0006

Data Index: 33649 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0751. Min Act: -0.0006

Data Index: 477495 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0813. Min Act: -0.0006

Data Index: 806268 (C4 (Web Text))

Max Activating Token Index: 345