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

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

Neuron 3100 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: 0.1014. Min Range: -0.1014

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1229736 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.1014. Min Act: -0.0002

Data Index: 582315 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0856. Min Act: -0.0002

Data Index: 352426 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0879. Min Act: -0.0002

Data Index: 429439 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1397329 (Python Code)

Max Activating Token Index: 427

Text #5

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1285395 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1243812 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1426077 (Python Code)

Max Activating Token Index: 401

Text #8

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0804. Min Act: -0.0002

Data Index: 801649 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0816. Min Act: -0.0002

Data Index: 430427 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1271924 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1057879 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0753. Min Act: -0.0002

Data Index: 554024 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1095574 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0774. Min Act: -0.0002

Data Index: 677519 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0748. Min Act: -0.0002

Data Index: 470471 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1007895 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1317983 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1278997 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0794. Min Act: -0.0002

Data Index: 309777 (C4 (Web Text))

Max Activating Token Index: 122