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

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

Neuron 641 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: 0.0761. Min Range: -0.0761

Max Act: 0.0723. Min Act: -0.0002

Data Index: 515937 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1328345 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0761. Min Act: -0.0002

Data Index: 927823 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1199379 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0736. Min Act: -0.0002

Data Index: 803193 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0698. Min Act: -0.0002

Data Index: 431080 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1155051 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0737. Min Act: -0.0002

Data Index: 131736 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0655. Min Act: -0.0002

Data Index: 301003 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1087145 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1014263 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0681. Min Act: -0.0002

Data Index: 638771 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1280129 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1143136 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0709. Min Act: -0.0002

Data Index: 175185 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0678. Min Act: -0.0002

Data Index: 529698 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0690. Min Act: -0.0002

Data Index: 585491 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0694. Min Act: -0.0002

Data Index: 350548 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0722. Min Act: -0.0002

Data Index: 97414 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0637. Min Act: -0.0002

Data Index: 884621 (C4 (Web Text))

Max Activating Token Index: 689