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

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

Neuron 200 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0001

Data Index: 803133 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0944. Min Act: -0.0001

Data Index: 480369 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0812. Min Act: -0.0001

Data Index: 410524 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0832. Min Act: -0.0001

Data Index: 84499 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0813. Min Act: -0.0002

Data Index: 771970 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0744. Min Act: -0.0001

Data Index: 520125 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1034769 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0490. Min Act: -0.0001

Data Index: 591961 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0760. Min Act: -0.0001

Data Index: 793612 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0651. Min Act: -0.0001

Data Index: 962253 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0652. Min Act: -0.0001

Data Index: 734957 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1354047 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0670. Min Act: -0.0001

Data Index: 253606 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1007080 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0658. Min Act: -0.0001

Data Index: 293126 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0714. Min Act: -0.0001

Data Index: 92005 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1348639 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0698. Min Act: -0.0001

Data Index: 775734 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0745. Min Act: -0.0001

Data Index: 789322 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1146169 (C4 (Web Text))

Max Activating Token Index: 917