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

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

Neuron 2092 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: 0.0010. Min Range: -0.0010

Max Act: 0.0010. Min Act: -0.0002

Data Index: 243984 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0008. Min Act: -0.0002

Data Index: 590143 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1089876 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1120794 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0007. Min Act: -0.0002

Data Index: 800738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1238543 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0006. Min Act: -0.0002

Data Index: 382953 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0006. Min Act: -0.0002

Data Index: 394664 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0006. Min Act: -0.0002

Data Index: 207283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0006. Min Act: -0.0002

Data Index: 346637 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0006. Min Act: -0.0002

Data Index: 364473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0006. Min Act: -0.0002

Data Index: 564357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0006. Min Act: -0.0002

Data Index: 60684 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0006. Min Act: -0.0001

Data Index: 1485623 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0005. Min Act: -0.0002

Data Index: 606695 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0005. Min Act: -0.0002

Data Index: 598854 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0005. Min Act: -0.0002

Data Index: 342124 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0005. Min Act: -0.0002

Data Index: 213764 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1145943 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0010. Min Range: -0.0010

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1506385 (Python Code)

Max Activating Token Index: 1023