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

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

Neuron 222 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0759. Min Act: -0.0001

Data Index: 237547 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0795. Min Act: -0.0001

Data Index: 815161 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0782. Min Act: -0.0001

Data Index: 839157 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0752. Min Act: -0.0001

Data Index: 250083 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0743. Min Act: -0.0001

Data Index: 191350 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0689. Min Act: -0.0001

Data Index: 88405 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1507593 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0713. Min Act: -0.0001

Data Index: 471863 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1024293 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1025908 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1644721 (Python Code)

Max Activating Token Index: 427

Text #11

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1427020 (Python Code)

Max Activating Token Index: 641

Text #12

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0689. Min Act: -0.0000

Data Index: 2687 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0686. Min Act: -0.0001

Data Index: 619787 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0686. Min Act: -0.0001

Data Index: 203793 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1508818 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0686. Min Act: -0.0001

Data Index: 994693 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0685. Min Act: -0.0001

Data Index: 944563 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0684. Min Act: -0.0000

Data Index: 535209 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0706. Min Act: -0.0001

Data Index: 755290 (C4 (Web Text))

Max Activating Token Index: 463