Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2695 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1290. Min Act: -0.0001

Data Index: 302820 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1098. Min Act: -0.0001

Data Index: 124201 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1012. Min Act: -0.0001

Data Index: 441699 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1004. Min Act: -0.0001

Data Index: 74293 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0905. Min Act: -0.0001

Data Index: 660 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0946. Min Act: -0.0001

Data Index: 523359 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0820. Min Act: -0.0001

Data Index: 134853 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0790. Min Act: -0.0001

Data Index: 453767 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0834. Min Act: -0.0001

Data Index: 611113 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0824. Min Act: -0.0001

Data Index: 706666 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0857. Min Act: -0.0001

Data Index: 783231 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0789. Min Act: -0.0001

Data Index: 369770 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1226822 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0832. Min Act: -0.0001

Data Index: 925260 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1211794 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0763. Min Act: -0.0001

Data Index: 450732 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0791. Min Act: -0.0001

Data Index: 218308 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0753. Min Act: -0.0001

Data Index: 610163 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0745. Min Act: -0.0001

Data Index: 302095 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0688. Min Act: -0.0001

Data Index: 173859 (C4 (Web Text))

Max Activating Token Index: 886