Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1681 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0928. Min Act: -0.0003

Data Index: 1619789 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0839. Min Act: -0.0003

Data Index: 517488 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0833. Min Act: -0.0003

Data Index: 1022788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1628394 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0686. Min Act: -0.0003

Data Index: 813603 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0795. Min Act: -0.0003

Data Index: 1500801 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0797. Min Act: -0.0003

Data Index: 224598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0786. Min Act: -0.0003

Data Index: 171581 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1216067 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0770. Min Act: -0.0003

Data Index: 780056 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0793. Min Act: -0.0003

Data Index: 623848 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0790. Min Act: -0.0003

Data Index: 1115522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0785. Min Act: -0.0003

Data Index: 978513 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0796. Min Act: -0.0003

Data Index: 587983 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0756. Min Act: -0.0003

Data Index: 195813 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1433600 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0783. Min Act: -0.0003

Data Index: 224400 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0787. Min Act: -0.0003

Data Index: 1169515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0785. Min Act: -0.0003

Data Index: 129515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0779. Min Act: -0.0003

Data Index: 782064 (C4 (Web Text))

Max Activating Token Index: 1023