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

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

Neuron 4978 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0000

Data Index: 247274 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1620595 (Python Code)

Max Activating Token Index: 454

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1225706 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0841. Min Act: -0.0000

Data Index: 123970 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0770. Min Act: -0.0000

Data Index: 531156 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1473456 (Python Code)

Max Activating Token Index: 526

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1645182 (Python Code)

Max Activating Token Index: 713

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0690. Min Act: -0.0000

Data Index: 220050 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1524518 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1479500 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1110344 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1450586 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1446613 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1639243 (Python Code)

Max Activating Token Index: 225

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1452474 (Python Code)

Max Activating Token Index: 485

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1498046 (Python Code)

Max Activating Token Index: 548

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0643. Min Act: -0.0000

Data Index: 427791 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1596862 (Python Code)

Max Activating Token Index: 755

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1039627 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0615. Min Act: -0.0000

Data Index: 10125 (C4 (Web Text))

Max Activating Token Index: 562