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

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

Neuron 558 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1042. Min Act: -0.0005

Data Index: 775060 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0742. Min Act: -0.0005

Data Index: 1308712 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0955. Min Act: -0.0005

Data Index: 929490 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0725. Min Act: -0.0005

Data Index: 228896 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0806. Min Act: -0.0005

Data Index: 792736 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0799. Min Act: -0.0005

Data Index: 103810 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0810. Min Act: -0.0004

Data Index: 527882 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0779. Min Act: -0.0005

Data Index: 313526 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0790. Min Act: -0.0005

Data Index: 1295813 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0677. Min Act: -0.0005

Data Index: 633804 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0735. Min Act: -0.0005

Data Index: 1277227 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0755. Min Act: -0.0005

Data Index: 535328 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0755. Min Act: -0.0005

Data Index: 172122 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0753. Min Act: -0.0005

Data Index: 764845 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0739. Min Act: -0.0005

Data Index: 355674 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0726. Min Act: -0.0005

Data Index: 97007 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0727. Min Act: -0.0005

Data Index: 1166389 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0677. Min Act: -0.0004

Data Index: 718869 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0704. Min Act: -0.0005

Data Index: 437097 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0694. Min Act: -0.0004

Data Index: 1122782 (C4 (Web Text))

Max Activating Token Index: 446