Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1698 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0984. Min Act: -0.0001

Data Index: 675738 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0905. Min Act: -0.0001

Data Index: 74019 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1254362 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1315576 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0760. Min Act: -0.0001

Data Index: 243734 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0756. Min Act: -0.0001

Data Index: 753970 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0764. Min Act: -0.0001

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0732. Min Act: -0.0001

Data Index: 544618 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0701. Min Act: -0.0001

Data Index: 128103 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1420949 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0735. Min Act: -0.0001

Data Index: 699644 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1586069 (Python Code)

Max Activating Token Index: 450

Text #12

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1513476 (Python Code)

Max Activating Token Index: 275

Text #13

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0695. Min Act: -0.0001

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1431033 (Python Code)

Max Activating Token Index: 228

Text #15

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1044065 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1439754 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0651. Min Act: -0.0001

Data Index: 129816 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0681. Min Act: -0.0001

Data Index: 655634 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1078309 (C4 (Web Text))

Max Activating Token Index: 928