Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2677 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0732. Min Act: -0.0002

Data Index: 936956 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0709. Min Act: -0.0002

Data Index: 500861 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0664. Min Act: -0.0002

Data Index: 158996 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0680. Min Act: -0.0002

Data Index: 474594 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0642. Min Act: -0.0002

Data Index: 623023 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0625. Min Act: -0.0002

Data Index: 574551 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0629. Min Act: -0.0002

Data Index: 440492 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0616. Min Act: -0.0002

Data Index: 127231 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0589. Min Act: -0.0002

Data Index: 403744 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0580. Min Act: -0.0002

Data Index: 496260 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0555. Min Act: -0.0002

Data Index: 303200 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0550. Min Act: -0.0002

Data Index: 769949 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0568. Min Act: -0.0002

Data Index: 869521 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0541. Min Act: -0.0002

Data Index: 684145 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0586. Min Act: -0.0002

Data Index: 386614 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0580. Min Act: -0.0002

Data Index: 662294 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0559. Min Act: -0.0002

Data Index: 155569 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1189654 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1003692 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1257518 (C4 (Web Text))

Max Activating Token Index: 195