Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3481 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0973. Min Act: -0.0000

Data Index: 897607 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1521182 (Python Code)

Max Activating Token Index: 893

Text #2

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0844. Min Act: -0.0001

Data Index: 331227 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1243983 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1619086 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1639004 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0686. Min Act: -0.0001

Data Index: 957307 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0610. Min Act: -0.0001

Data Index: 179545 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0600. Min Act: -0.0001

Data Index: 646149 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0599. Min Act: -0.0001

Data Index: 891642 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0623. Min Act: -0.0001

Data Index: 257011 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1099079 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1054814 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0553. Min Act: -0.0001

Data Index: 466387 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0590. Min Act: -0.0001

Data Index: 391046 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0595. Min Act: -0.0001

Data Index: 163548 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0625. Min Act: -0.0001

Data Index: 535684 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0586. Min Act: -0.0001

Data Index: 100385 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1408829 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0580. Min Act: -0.0001

Data Index: 571274 (C4 (Web Text))

Max Activating Token Index: 382