Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 325 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0739. Min Act: -0.0004

Data Index: 94459 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0822. Min Act: -0.0005

Data Index: 277472 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0700. Min Act: -0.0005

Data Index: 676056 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0722. Min Act: -0.0005

Data Index: 138545 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0690. Min Act: -0.0005

Data Index: 822354 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0726. Min Act: -0.0005

Data Index: 149421 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0666. Min Act: -0.0005

Data Index: 1311792 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0736. Min Act: -0.0005

Data Index: 562786 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0693. Min Act: -0.0005

Data Index: 407836 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0729. Min Act: -0.0004

Data Index: 844804 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0746. Min Act: -0.0005

Data Index: 947412 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0698. Min Act: -0.0004

Data Index: 1351114 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0680. Min Act: -0.0005

Data Index: 1185412 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0679. Min Act: -0.0004

Data Index: 396762 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0642. Min Act: -0.0005

Data Index: 660977 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0647. Min Act: -0.0005

Data Index: 103566 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0631. Min Act: -0.0005

Data Index: 807702 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0608. Min Act: -0.0005

Data Index: 987570 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0605. Min Act: -0.0005

Data Index: 911551 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0654. Min Act: -0.0005

Data Index: 1347222 (C4 (Web Text))

Max Activating Token Index: 775