Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 6 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0002

Data Index: 554832 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0927. Min Act: -0.0002

Data Index: 807649 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0939. Min Act: -0.0002

Data Index: 158314 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0834. Min Act: -0.0002

Data Index: 808551 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0747. Min Act: -0.0002

Data Index: 329285 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0784. Min Act: -0.0002

Data Index: 545213 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0881. Min Act: -0.0002

Data Index: 103426 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0724. Min Act: -0.0002

Data Index: 226545 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0801. Min Act: -0.0002

Data Index: 489666 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0766. Min Act: -0.0002

Data Index: 434400 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1049691 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0813. Min Act: -0.0002

Data Index: 168577 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0832. Min Act: -0.0002

Data Index: 861330 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0846. Min Act: -0.0002

Data Index: 371446 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1134077 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0716. Min Act: -0.0002

Data Index: 983927 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0667. Min Act: -0.0002

Data Index: 904495 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1304104 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0756. Min Act: -0.0002

Data Index: 821763 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0695. Min Act: -0.0002

Data Index: 971946 (C4 (Web Text))

Max Activating Token Index: 126