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

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

Neuron 331 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1320756 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0747. Min Act: -0.0001

Data Index: 388494 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1096326 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1215908 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0652. Min Act: -0.0001

Data Index: 391056 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0679. Min Act: -0.0001

Data Index: 103595 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0625. Min Act: -0.0001

Data Index: 426480 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0637. Min Act: -0.0001

Data Index: 85090 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0631. Min Act: -0.0001

Data Index: 264769 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0647. Min Act: -0.0001

Data Index: 340536 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0643. Min Act: -0.0001

Data Index: 333049 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0616. Min Act: -0.0001

Data Index: 820113 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1113689 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1166893 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1428359 (Python Code)

Max Activating Token Index: 496

Text #15

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0639. Min Act: -0.0001

Data Index: 638639 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0613. Min Act: -0.0001

Data Index: 920954 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0580. Min Act: -0.0001

Data Index: 309440 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0644. Min Act: -0.0001

Data Index: 854275 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1013039 (C4 (Web Text))

Max Activating Token Index: 665