Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1704 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1606975 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0043. Min Act: -0.0006

Data Index: 701135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0041. Min Act: -0.0006

Data Index: 1461943 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0040. Min Act: -0.0006

Data Index: 1656032 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0038. Min Act: -0.0006

Data Index: 1363728 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0038. Min Act: -0.0006

Data Index: 175903 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0036. Min Act: -0.0006

Data Index: 1645779 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0036. Min Act: -0.0005

Data Index: 1422754 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0037. Min Act: -0.0006

Data Index: 429439 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0035. Min Act: -0.0005

Data Index: 1549488 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0034. Min Act: -0.0006

Data Index: 1242052 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0035. Min Act: -0.0006

Data Index: 1382554 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0035. Min Act: -0.0006

Data Index: 1442305 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0034. Min Act: -0.0006

Data Index: 1499401 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0034. Min Act: -0.0006

Data Index: 1475527 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0032. Min Act: -0.0006

Data Index: 1429552 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1519652 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0032. Min Act: -0.0006

Data Index: 627483 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0033. Min Act: -0.0006

Data Index: 1653926 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0034. Min Act: -0.0006

Data Index: 921629 (C4 (Web Text))

Max Activating Token Index: 1023