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

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

Neuron 249 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5221. Min Range: -2.5221

Max Act: 2.5221. Min Act: -0.0000

Data Index: 1436591 (Python Code)

Max Activating Token Index: 915

Text #1

Max Range: 2.5221. Min Range: -2.5221

Max Act: 2.2253. Min Act: -0.0000

Data Index: 22301 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.9671. Min Act: -0.0000

Data Index: 295493 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 2.5221. Min Range: -2.5221

Max Act: 2.1056. Min Act: -0.0000

Data Index: 346656 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 2.5221. Min Range: -2.5221

Max Act: 2.0762. Min Act: -0.0000

Data Index: 687285 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 2.5221. Min Range: -2.5221

Max Act: 2.0050. Min Act: -0.0000

Data Index: 362423 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.7280. Min Act: -0.0000

Data Index: 595489 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.7904. Min Act: -0.0000

Data Index: 1090233 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.8215. Min Act: -0.0000

Data Index: 826528 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.7474. Min Act: -0.0000

Data Index: 294881 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.6700. Min Act: -0.0000

Data Index: 997136 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.7447. Min Act: -0.0000

Data Index: 558629 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.8111. Min Act: -0.0000

Data Index: 1193710 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.5691. Min Act: -0.0000

Data Index: 975567 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.7136. Min Act: -0.0000

Data Index: 340899 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.6680. Min Act: -0.0000

Data Index: 1557094 (Python Code)

Max Activating Token Index: 961

Text #16

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.6040. Min Act: -0.0000

Data Index: 1169631 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.7989. Min Act: -0.0000

Data Index: 523018 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.6128. Min Act: -0.0000

Data Index: 848835 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 2.5221. Min Range: -2.5221

Max Act: 1.7079. Min Act: -0.0000

Data Index: 314296 (C4 (Web Text))

Max Activating Token Index: 59