Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1922 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0006

Data Index: 963708 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0673. Min Act: -0.0006

Data Index: 1251834 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0664. Min Act: -0.0006

Data Index: 1054214 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0630. Min Act: -0.0006

Data Index: 628573 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0612. Min Act: -0.0006

Data Index: 138421 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0627. Min Act: -0.0006

Data Index: 68896 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0622. Min Act: -0.0006

Data Index: 907580 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0581. Min Act: -0.0006

Data Index: 999286 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0589. Min Act: -0.0006

Data Index: 397221 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0590. Min Act: -0.0006

Data Index: 1256625 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0587. Min Act: -0.0006

Data Index: 592555 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0574. Min Act: -0.0006

Data Index: 768759 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0578. Min Act: -0.0006

Data Index: 1059674 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0566. Min Act: -0.0006

Data Index: 507735 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0577. Min Act: -0.0006

Data Index: 740379 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0587. Min Act: -0.0006

Data Index: 662692 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0558. Min Act: -0.0006

Data Index: 905207 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0578. Min Act: -0.0006

Data Index: 1085573 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0555. Min Act: -0.0006

Data Index: 247284 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0553. Min Act: -0.0006

Data Index: 951002 (C4 (Web Text))

Max Activating Token Index: 779