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

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

Neuron 4519 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: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1026426 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 255253 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 450736 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 218196 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1109918 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 969771 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 10049 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 863261 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 383769 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1175722 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 843096 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1040729 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 844266 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1231173 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 867582 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 210631 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1278134 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 506229 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 314064 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 858290 (C4 (Web Text))

Max Activating Token Index: 2