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

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

Neuron 5297 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: 0.0881. Min Range: -0.0881

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1637407 (Python Code)

Max Activating Token Index: 155

Text #1

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0859. Min Act: -0.0002

Data Index: 771575 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1398986 (Python Code)

Max Activating Token Index: 377

Text #3

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0804. Min Act: -0.0002

Data Index: 695484 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1530187 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0793. Min Act: -0.0002

Data Index: 779610 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0789. Min Act: -0.0002

Data Index: 695262 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0770. Min Act: -0.0002

Data Index: 52957 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0774. Min Act: -0.0002

Data Index: 400516 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0754. Min Act: -0.0002

Data Index: 711751 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0760. Min Act: -0.0002

Data Index: 203858 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0756. Min Act: -0.0002

Data Index: 378361 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0754. Min Act: -0.0002

Data Index: 470396 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0745. Min Act: -0.0002

Data Index: 330337 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1517193 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1223878 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1301705 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0733. Min Act: -0.0002

Data Index: 430883 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1315479 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1528122 (Python Code)

Max Activating Token Index: 251