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

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

Neuron 3634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1657. Min Range: -1.1657

Max Act: 1.1657. Min Act: -0.0000

Data Index: 633435 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.1657. Min Range: -1.1657

Max Act: 1.1167. Min Act: -0.0000

Data Index: 646119 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.1657. Min Range: -1.1657

Max Act: 1.0048. Min Act: -0.0000

Data Index: 60085 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.1657. Min Range: -1.1657

Max Act: 1.0281. Min Act: -0.0000

Data Index: 135455 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9197. Min Act: -0.0000

Data Index: 832701 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9407. Min Act: -0.0000

Data Index: 615189 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9868. Min Act: -0.0000

Data Index: 550416 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9267. Min Act: -0.0000

Data Index: 57900 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8880. Min Act: -0.0000

Data Index: 845788 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1096601 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8767. Min Act: -0.0000

Data Index: 78605 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9216. Min Act: -0.0001

Data Index: 528786 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1319100 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1135422 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1107769 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9269. Min Act: -0.0000

Data Index: 730746 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8707. Min Act: -0.0000

Data Index: 142772 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8650. Min Act: -0.0000

Data Index: 885992 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8812. Min Act: -0.0000

Data Index: 444182 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8849. Min Act: -0.0000

Data Index: 515814 (C4 (Web Text))

Max Activating Token Index: 966