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

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

Neuron 121 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: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 114584 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 177780 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 393865 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 396251 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 719473 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 818760 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 952439 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1294324 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1140952 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 412151 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 979122 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 988199 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 597966 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0083. Min Act: -0.0002

Data Index: 690897 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0076. Min Act: -0.0002

Data Index: 75398 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0074. Min Act: -0.0002

Data Index: 899149 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0073. Min Act: -0.0002

Data Index: 598498 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0073. Min Act: -0.0002

Data Index: 252368 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0072. Min Act: -0.0002

Data Index: 273958 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0072. Min Act: -0.0002

Data Index: 264170 (C4 (Web Text))

Max Activating Token Index: 1