Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 687 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.1128. Min Act: -0.0003

Data Index: 510950 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.1059. Min Act: -0.0003

Data Index: 139697 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0969. Min Act: -0.0003

Data Index: 1260387 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0932. Min Act: -0.0003

Data Index: 656841 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0983. Min Act: -0.0003

Data Index: 323476 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0908. Min Act: -0.0003

Data Index: 1005364 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0862. Min Act: -0.0003

Data Index: 377442 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0894. Min Act: -0.0003

Data Index: 666324 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0849. Min Act: -0.0003

Data Index: 813539 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0839. Min Act: -0.0003

Data Index: 536611 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1433850 (Python Code)

Max Activating Token Index: 604

Text #11

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0895. Min Act: -0.0003

Data Index: 1080311 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0829. Min Act: -0.0003

Data Index: 170962 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0841. Min Act: -0.0003

Data Index: 784894 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0837. Min Act: -0.0003

Data Index: 558742 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0776. Min Act: -0.0003

Data Index: 61346 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0785. Min Act: -0.0003

Data Index: 519857 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0775. Min Act: -0.0003

Data Index: 101855 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0772. Min Act: -0.0003

Data Index: 903889 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0788. Min Act: -0.0003

Data Index: 321615 (C4 (Web Text))

Max Activating Token Index: 61