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

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

Neuron 164 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0000

Data Index: 956670 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0771. Min Act: -0.0000

Data Index: 455588 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0871. Min Act: -0.0000

Data Index: 834063 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1122300 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0768. Min Act: -0.0001

Data Index: 322111 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1624867 (Python Code)

Max Activating Token Index: 961

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1107710 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0759. Min Act: -0.0000

Data Index: 955798 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0811. Min Act: -0.0001

Data Index: 712441 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0702. Min Act: -0.0001

Data Index: 312729 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0747. Min Act: -0.0000

Data Index: 377140 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0724. Min Act: -0.0001

Data Index: 5143 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1267217 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0786. Min Act: -0.0000

Data Index: 216117 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0733. Min Act: -0.0000

Data Index: 159412 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1088281 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0765. Min Act: -0.0000

Data Index: 157304 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1241413 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0706. Min Act: -0.0000

Data Index: 976663 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0729. Min Act: -0.0000

Data Index: 20948 (C4 (Web Text))

Max Activating Token Index: 796