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

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

Neuron 4573 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.3878. Min Act: -0.0001

Data Index: 86591 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.0149. Min Act: -0.0001

Data Index: 225987 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.3878. Min Range: -1.3878

Max Act: 1.0232. Min Act: -0.0001

Data Index: 823940 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.9069. Min Act: -0.0001

Data Index: 1141116 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.9659. Min Act: -0.0001

Data Index: 131214 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.9107. Min Act: -0.0001

Data Index: 1220519 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.9274. Min Act: -0.0001

Data Index: 176467 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.9710. Min Act: -0.0001

Data Index: 455196 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8819. Min Act: -0.0001

Data Index: 360483 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8986. Min Act: -0.0001

Data Index: 956286 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.9004. Min Act: -0.0001

Data Index: 374731 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8945. Min Act: -0.0001

Data Index: 13832 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8875. Min Act: -0.0001

Data Index: 628756 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8617. Min Act: -0.0001

Data Index: 308936 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8523. Min Act: -0.0001

Data Index: 894777 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8793. Min Act: -0.0001

Data Index: 1269884 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.9072. Min Act: -0.0001

Data Index: 547075 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8596. Min Act: -0.0001

Data Index: 1343488 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8482. Min Act: -0.0001

Data Index: 1139874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.3878. Min Range: -1.3878

Max Act: 0.8245. Min Act: -0.0001

Data Index: 48697 (C4 (Web Text))

Max Activating Token Index: 168