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

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

Neuron 4922 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: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0002

Data Index: 774527 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1278614 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0888. Min Act: -0.0002

Data Index: 427651 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0883. Min Act: -0.0002

Data Index: 66250 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0868. Min Act: -0.0002

Data Index: 513721 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0849. Min Act: -0.0002

Data Index: 516170 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1212793 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0818. Min Act: -0.0002

Data Index: 988024 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1048202 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0820. Min Act: -0.0002

Data Index: 994031 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0830. Min Act: -0.0002

Data Index: 860106 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0793. Min Act: -0.0002

Data Index: 255417 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0810. Min Act: -0.0002

Data Index: 489671 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1153512 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0803. Min Act: -0.0002

Data Index: 503488 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0794. Min Act: -0.0002

Data Index: 323608 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1128091 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0786. Min Act: -0.0002

Data Index: 839899 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0798. Min Act: -0.0002

Data Index: 529497 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0777. Min Act: -0.0002

Data Index: 756355 (C4 (Web Text))

Max Activating Token Index: 300