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

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

Neuron 4828 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: 0.0906. Min Range: -0.0906

Max Act: 0.0906. Min Act: -0.0002

Data Index: 35939 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0805. Min Act: -0.0002

Data Index: 682675 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0894. Min Act: -0.0002

Data Index: 489349 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0779. Min Act: -0.0002

Data Index: 210240 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0819. Min Act: -0.0002

Data Index: 136746 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0774. Min Act: -0.0002

Data Index: 40481 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0832. Min Act: -0.0002

Data Index: 314526 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1075510 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0818. Min Act: -0.0002

Data Index: 529963 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0810. Min Act: -0.0002

Data Index: 445689 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0785. Min Act: -0.0002

Data Index: 766732 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0723. Min Act: -0.0002

Data Index: 360966 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1181531 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1271311 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0820. Min Act: -0.0002

Data Index: 41559 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0765. Min Act: -0.0002

Data Index: 293518 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0843. Min Act: -0.0002

Data Index: 635747 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0706. Min Act: -0.0002

Data Index: 82116 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1350554 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0779. Min Act: -0.0002

Data Index: 326519 (C4 (Web Text))

Max Activating Token Index: 670