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

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

Neuron 1639 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: 0.0857. Min Range: -0.0857

Max Act: 0.0843. Min Act: -0.0003

Data Index: 198818 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0857. Min Act: -0.0003

Data Index: 777 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0769. Min Act: -0.0003

Data Index: 843614 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1201453 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1278779 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0682. Min Act: -0.0003

Data Index: 610140 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0671. Min Act: -0.0003

Data Index: 539465 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0670. Min Act: -0.0003

Data Index: 697737 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0688. Min Act: -0.0003

Data Index: 894425 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0626. Min Act: -0.0003

Data Index: 168080 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0684. Min Act: -0.0003

Data Index: 632949 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1168376 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0661. Min Act: -0.0003

Data Index: 417714 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1350244 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0623. Min Act: -0.0003

Data Index: 918406 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0603. Min Act: -0.0003

Data Index: 446043 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0649. Min Act: -0.0003

Data Index: 319783 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1050627 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0593. Min Act: -0.0003

Data Index: 101584 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0601. Min Act: -0.0003

Data Index: 792500 (C4 (Web Text))

Max Activating Token Index: 104