Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5748 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.2115. Min Act: -0.0001

Data Index: 348299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1037890 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1115071 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1187. Min Act: -0.0001

Data Index: 270147 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1166. Min Act: -0.0001

Data Index: 913732 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1045. Min Act: -0.0001

Data Index: 293405 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1122905 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0961. Min Act: -0.0001

Data Index: 872416 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0925. Min Act: -0.0001

Data Index: 449268 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1239585 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1056471 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0716. Min Act: -0.0001

Data Index: 14614 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0825. Min Act: -0.0001

Data Index: 873132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1005046 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0727. Min Act: -0.0001

Data Index: 673874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0734. Min Act: -0.0001

Data Index: 298299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0715. Min Act: -0.0001

Data Index: 426768 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0558. Min Act: -0.0001

Data Index: 675833 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0630. Min Act: -0.0001

Data Index: 128735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.0522. Min Act: -0.0001

Data Index: 435415 (C4 (Web Text))

Max Activating Token Index: 1023