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

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

Neuron 1569 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0002

Data Index: 789647 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0774. Min Act: -0.0002

Data Index: 492596 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0738. Min Act: -0.0002

Data Index: 123289 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1071782 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0718. Min Act: -0.0002

Data Index: 480841 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0704. Min Act: -0.0002

Data Index: 365889 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0729. Min Act: -0.0002

Data Index: 487121 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0722. Min Act: -0.0002

Data Index: 208197 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1219532 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1028023 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1345103 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0718. Min Act: -0.0002

Data Index: 171464 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0716. Min Act: -0.0002

Data Index: 247931 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0723. Min Act: -0.0002

Data Index: 169873 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0696. Min Act: -0.0002

Data Index: 618813 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0702. Min Act: -0.0002

Data Index: 310108 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0697. Min Act: -0.0002

Data Index: 815446 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0704. Min Act: -0.0002

Data Index: 899930 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1336429 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0697. Min Act: -0.0002

Data Index: 619998 (C4 (Web Text))

Max Activating Token Index: 9