Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2731 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1047. Min Act: -0.0002

Data Index: 679092 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1014. Min Act: -0.0002

Data Index: 667298 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1010. Min Act: -0.0002

Data Index: 110375 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0944. Min Act: -0.0002

Data Index: 939594 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0934. Min Act: -0.0002

Data Index: 466876 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1207528 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0906. Min Act: -0.0002

Data Index: 918662 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0896. Min Act: -0.0002

Data Index: 861292 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1100617 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0887. Min Act: -0.0002

Data Index: 152850 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0877. Min Act: -0.0002

Data Index: 8682 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0859. Min Act: -0.0002

Data Index: 400737 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0879. Min Act: -0.0002

Data Index: 629234 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0882. Min Act: -0.0002

Data Index: 144866 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1333666 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0822. Min Act: -0.0002

Data Index: 164200 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1221181 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0843. Min Act: -0.0002

Data Index: 846760 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0798. Min Act: -0.0002

Data Index: 99337 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0810. Min Act: -0.0002

Data Index: 601828 (C4 (Web Text))

Max Activating Token Index: 573