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

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

Neuron 3326 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1044158 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0002

Data Index: 1306221 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0002

Data Index: 180158 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1300076 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1354013 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1169399 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0002

Data Index: 239489 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0002

Data Index: 607524 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0002

Data Index: 968644 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0002

Data Index: 101735 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0002

Data Index: 233665 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0002

Data Index: 729162 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0002

Data Index: 611129 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0072. Min Act: -0.0002

Data Index: 727301 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1341098 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0072. Min Act: -0.0002

Data Index: 296727 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0072. Min Act: -0.0002

Data Index: 565265 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1083094 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0070. Min Act: -0.0002

Data Index: 66732 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0071. Min Act: -0.0002

Data Index: 838483 (C4 (Web Text))

Max Activating Token Index: 301