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

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

Neuron 5073 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: 0.0031. Min Range: -0.0031

Max Act: 0.0031. Min Act: -0.0002

Data Index: 459617 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0024. Min Act: -0.0002

Data Index: 378958 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0023. Min Act: -0.0002

Data Index: 182584 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0023. Min Act: -0.0002

Data Index: 289235 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1028503 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0022. Min Act: -0.0002

Data Index: 773292 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1072108 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0022. Min Act: -0.0002

Data Index: 230412 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0022. Min Act: -0.0002

Data Index: 226310 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1310052 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1308587 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 235347 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 181798 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1090209 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 164007 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 968646 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 368663 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 430715 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1105746 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0031. Min Range: -0.0031

Max Act: 0.0021. Min Act: -0.0002

Data Index: 232543 (C4 (Web Text))

Max Activating Token Index: 820