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

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

Neuron 1849 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.1277. Min Act: -0.0005

Data Index: 513205 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0977. Min Act: -0.0005

Data Index: 303657 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0922. Min Act: -0.0005

Data Index: 878896 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0829. Min Act: -0.0005

Data Index: 908360 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0808. Min Act: -0.0005

Data Index: 1340550 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0822. Min Act: -0.0005

Data Index: 556533 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0758. Min Act: -0.0005

Data Index: 214037 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0769. Min Act: -0.0005

Data Index: 1031764 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0765. Min Act: -0.0005

Data Index: 766227 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0741. Min Act: -0.0005

Data Index: 745366 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0755. Min Act: -0.0005

Data Index: 1087420 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0730. Min Act: -0.0005

Data Index: 767226 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0756. Min Act: -0.0005

Data Index: 954048 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0673. Min Act: -0.0005

Data Index: 555544 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0676. Min Act: -0.0005

Data Index: 1100554 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0736. Min Act: -0.0005

Data Index: 1232439 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0673. Min Act: -0.0005

Data Index: 1221107 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0723. Min Act: -0.0005

Data Index: 1172870 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0730. Min Act: -0.0005

Data Index: 1331473 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.1277. Min Range: -0.1277

Max Act: 0.0723. Min Act: -0.0005

Data Index: 1057157 (C4 (Web Text))

Max Activating Token Index: 198