Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 66 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1063289 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0039. Min Act: -0.0006

Data Index: 110683 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0005

Data Index: 1589808 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 1123259 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0006

Data Index: 974305 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0006

Data Index: 975319 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0006

Data Index: 691535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0006

Data Index: 806951 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0035. Min Act: -0.0006

Data Index: 951038 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0035. Min Act: -0.0006

Data Index: 1063939 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0035. Min Act: -0.0006

Data Index: 988467 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0034. Min Act: -0.0006

Data Index: 107491 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0034. Min Act: -0.0006

Data Index: 1137310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0034. Min Act: -0.0006

Data Index: 5801 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0033. Min Act: -0.0006

Data Index: 963050 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0033. Min Act: -0.0006

Data Index: 196376 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0033. Min Act: -0.0006

Data Index: 438361 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0032. Min Act: -0.0006

Data Index: 501205 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0033. Min Act: -0.0006

Data Index: 559414 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0032. Min Act: -0.0006

Data Index: 1101779 (C4 (Web Text))

Max Activating Token Index: 1023