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

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

Neuron 1082 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1388406 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0002

Data Index: 990815 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0002

Data Index: 656127 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0002

Data Index: 585530 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 324397 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1254409 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 512816 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1647089 (Python Code)

Max Activating Token Index: 674

Text #8

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 296349 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0003

Data Index: 1289553 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 342204 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 622340 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0003

Data Index: 1294505 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0003

Data Index: 1343613 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 634575 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0002

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1260256 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 770893 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1236207 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0004. Min Act: -0.0002

Data Index: 246176 (C4 (Web Text))

Max Activating Token Index: 1023