Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3780 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0690. Min Range: -2.0690

Max Act: 2.0690. Min Act: -0.0000

Data Index: 522892 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.9780. Min Act: -0.0000

Data Index: 1006979 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.6923. Min Act: -0.0000

Data Index: 75979 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.6629. Min Act: -0.0000

Data Index: 577484 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.7051. Min Act: -0.0000

Data Index: 737297 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.5220. Min Act: -0.0000

Data Index: 984739 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.5357. Min Act: -0.0000

Data Index: 219262 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.5256. Min Act: -0.0000

Data Index: 1189691 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.5936. Min Act: -0.0000

Data Index: 907134 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.4905. Min Act: -0.0000

Data Index: 477618 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.5680. Min Act: -0.0000

Data Index: 1116091 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1149555 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.4779. Min Act: -0.0001

Data Index: 837072 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.4780. Min Act: -0.0000

Data Index: 448258 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.4769. Min Act: -0.0000

Data Index: 693547 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.3749. Min Act: -0.0000

Data Index: 396749 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.4585. Min Act: -0.0001

Data Index: 1170281 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.4900. Min Act: -0.0001

Data Index: 224936 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.4871. Min Act: -0.0000

Data Index: 982677 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 2.0690. Min Range: -2.0690

Max Act: 1.3939. Min Act: -0.0000

Data Index: 1203060 (C4 (Web Text))

Max Activating Token Index: 668