Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3019 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0003

Data Index: 1477895 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1383918 (Python Code)

Max Activating Token Index: 873

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0808. Min Act: -0.0003

Data Index: 358908 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0748. Min Act: -0.0003

Data Index: 450868 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1597215 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0699. Min Act: -0.0003

Data Index: 40639 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1656778 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0708. Min Act: -0.0003

Data Index: 544408 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0747. Min Act: -0.0003

Data Index: 357421 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1000141 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1302536 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1523822 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0710. Min Act: -0.0003

Data Index: 900601 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0675. Min Act: -0.0003

Data Index: 968780 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0706. Min Act: -0.0003

Data Index: 109637 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0687. Min Act: -0.0003

Data Index: 199541 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1608809 (Python Code)

Max Activating Token Index: 588

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0697. Min Act: -0.0003

Data Index: 1002880 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1305690 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0721. Min Act: -0.0003

Data Index: 739017 (C4 (Web Text))

Max Activating Token Index: 544