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

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

Neuron 1070 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0032. Min Act: -0.0002

Data Index: 573440 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0004. Min Act: -0.0001

Data Index: 402378 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0004. Min Act: -0.0002

Data Index: 78650 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1072077 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1246680 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0002. Min Act: -0.0001

Data Index: 687899 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0003. Min Act: -0.0002

Data Index: 196934 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0002. Min Act: -0.0001

Data Index: 1202401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1375545 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0002. Min Act: -0.0001

Data Index: 46920 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0002. Min Act: -0.0001

Data Index: 1036437 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0002. Min Act: -0.0002

Data Index: 942082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1620448 (Python Code)

Max Activating Token Index: 450

Text #13

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0001. Min Act: -0.0001

Data Index: 575814 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1415193 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0001. Min Act: -0.0002

Data Index: 980806 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0001. Min Act: -0.0002

Data Index: 280198 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0001. Min Act: -0.0001

Data Index: 231078 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0001. Min Act: -0.0002

Data Index: 330430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0001. Min Act: -0.0002

Data Index: 134285 (C4 (Web Text))

Max Activating Token Index: 1023