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

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

Neuron 3325 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0003

Data Index: 994995 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0888. Min Act: -0.0002

Data Index: 219017 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1336080 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0775. Min Act: -0.0003

Data Index: 993898 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0784. Min Act: -0.0003

Data Index: 1226247 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1286163 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0749. Min Act: -0.0003

Data Index: 742312 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0734. Min Act: -0.0003

Data Index: 755440 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0776. Min Act: -0.0003

Data Index: 677863 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1268109 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1312774 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1029850 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0662. Min Act: -0.0002

Data Index: 968957 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0678. Min Act: -0.0003

Data Index: 698798 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0654. Min Act: -0.0003

Data Index: 729756 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0684. Min Act: -0.0003

Data Index: 47403 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0647. Min Act: -0.0003

Data Index: 274926 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1299169 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0632. Min Act: -0.0003

Data Index: 237198 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0647. Min Act: -0.0003

Data Index: 280122 (C4 (Web Text))

Max Activating Token Index: 219