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

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

Neuron 4022 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: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0001

Data Index: 187538 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1035. Min Act: -0.0000

Data Index: 456128 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1307831 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0856. Min Act: -0.0001

Data Index: 553350 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0879. Min Act: -0.0001

Data Index: 474747 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0789. Min Act: -0.0001

Data Index: 772158 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1147077 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1051104 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1258678 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0714. Min Act: -0.0001

Data Index: 609274 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0724. Min Act: -0.0001

Data Index: 217016 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1284757 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0720. Min Act: -0.0000

Data Index: 907323 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1580453 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0718. Min Act: -0.0001

Data Index: 897459 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0744. Min Act: -0.0001

Data Index: 119027 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1105581 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1492487 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0675. Min Act: -0.0001

Data Index: 606932 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0724. Min Act: -0.0001

Data Index: 49650 (C4 (Web Text))

Max Activating Token Index: 140