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

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

Neuron 5904 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: 0.0007. Min Range: -0.0007

Max Act: 0.0007. Min Act: -0.0002

Data Index: 266803 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1388406 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1294505 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0005. Min Act: -0.0002

Data Index: 495216 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0005. Min Act: -0.0002

Data Index: 914495 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0005. Min Act: -0.0002

Data Index: 797284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0005. Min Act: -0.0002

Data Index: 773939 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0005. Min Act: -0.0002

Data Index: 652910 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0005. Min Act: -0.0003

Data Index: 51443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0005. Min Act: -0.0002

Data Index: 500341 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1278795 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 762419 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 167562 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1108662 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1620940 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 968658 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 184171 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 810425 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1564283 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0007. Min Range: -0.0007

Max Act: 0.0004. Min Act: -0.0002

Data Index: 340798 (C4 (Web Text))

Max Activating Token Index: 1023