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

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

Neuron 764 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: 0.0937. Min Range: -0.0937

Max Act: 0.0937. Min Act: -0.0005

Data Index: 922422 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0880. Min Act: -0.0005

Data Index: 1630735 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0853. Min Act: -0.0005

Data Index: 1023708 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0828. Min Act: -0.0005

Data Index: 236307 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0805. Min Act: -0.0005

Data Index: 468535 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0861. Min Act: -0.0005

Data Index: 918639 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0818. Min Act: -0.0005

Data Index: 1429101 (Python Code)

Max Activating Token Index: 305

Text #7

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0823. Min Act: -0.0005

Data Index: 763503 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0762. Min Act: -0.0005

Data Index: 1218884 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0782. Min Act: -0.0005

Data Index: 1589113 (Python Code)

Max Activating Token Index: 677

Text #10

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0815. Min Act: -0.0005

Data Index: 32312 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0772. Min Act: -0.0005

Data Index: 1142513 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0766. Min Act: -0.0005

Data Index: 104094 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0774. Min Act: -0.0005

Data Index: 665089 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0804. Min Act: -0.0005

Data Index: 1383235 (Python Code)

Max Activating Token Index: 1018

Text #15

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0777. Min Act: -0.0005

Data Index: 1394138 (Python Code)

Max Activating Token Index: 556

Text #16

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0732. Min Act: -0.0005

Data Index: 813448 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0760. Min Act: -0.0005

Data Index: 53729 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0763. Min Act: -0.0005

Data Index: 490806 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0758. Min Act: -0.0005

Data Index: 383776 (C4 (Web Text))

Max Activating Token Index: 30