Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 37 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0883. Min Act: -0.0002

Data Index: 926538 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0824. Min Act: -0.0002

Data Index: 900121 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0792. Min Act: -0.0002

Data Index: 905901 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0745. Min Act: -0.0002

Data Index: 255159 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0770. Min Act: -0.0002

Data Index: 606712 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0753. Min Act: -0.0002

Data Index: 278673 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0761. Min Act: -0.0002

Data Index: 809079 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1206786 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1013847 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0703. Min Act: -0.0002

Data Index: 460679 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0719. Min Act: -0.0002

Data Index: 245219 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0707. Min Act: -0.0002

Data Index: 28032 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0715. Min Act: -0.0002

Data Index: 939708 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1174934 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0682. Min Act: -0.0002

Data Index: 782812 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0685. Min Act: -0.0002

Data Index: 385249 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0664. Min Act: -0.0002

Data Index: 988915 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0687. Min Act: -0.0002

Data Index: 49493 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1246692 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.0883. Min Range: -0.0883

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1099922 (C4 (Web Text))

Max Activating Token Index: 604