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

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

Neuron 225 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: 0.1054. Min Range: -0.1054

Max Act: 0.1054. Min Act: -0.0002

Data Index: 613841 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0781. Min Act: -0.0002

Data Index: 258530 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0747. Min Act: -0.0002

Data Index: 220268 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1290111 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0782. Min Act: -0.0002

Data Index: 367564 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1063439 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1348950 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0699. Min Act: -0.0001

Data Index: 730805 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0712. Min Act: -0.0002

Data Index: 655355 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0738. Min Act: -0.0002

Data Index: 799803 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1183323 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0708. Min Act: -0.0002

Data Index: 789404 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0701. Min Act: -0.0002

Data Index: 366667 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0667. Min Act: -0.0002

Data Index: 38466 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0704. Min Act: -0.0002

Data Index: 553855 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0705. Min Act: -0.0002

Data Index: 584247 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0691. Min Act: -0.0002

Data Index: 496117 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0672. Min Act: -0.0002

Data Index: 868694 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0682. Min Act: -0.0002

Data Index: 321567 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0666. Min Act: -0.0002

Data Index: 311906 (C4 (Web Text))

Max Activating Token Index: 90