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

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

Neuron 1474 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0838. Min Act: -0.0001

Data Index: 291750 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1123935 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0832. Min Act: -0.0001

Data Index: 809973 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1244454 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0853. Min Act: -0.0001

Data Index: 472321 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0787. Min Act: -0.0001

Data Index: 34125 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0773. Min Act: -0.0001

Data Index: 658370 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0824. Min Act: -0.0001

Data Index: 269304 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0797. Min Act: -0.0001

Data Index: 655317 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0792. Min Act: -0.0001

Data Index: 612563 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1275308 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0771. Min Act: -0.0001

Data Index: 225230 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1202765 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0763. Min Act: -0.0001

Data Index: 571225 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0766. Min Act: -0.0001

Data Index: 768547 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1257854 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0777. Min Act: -0.0001

Data Index: 91437 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0756. Min Act: -0.0001

Data Index: 410685 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1146991 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1251792 (C4 (Web Text))

Max Activating Token Index: 429