Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 148 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0661. Min Act: -0.0004

Data Index: 1006654 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1302224 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1387632 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1465165 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0611. Min Act: -0.0003

Data Index: 118765 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1634821 (Python Code)

Max Activating Token Index: 574

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0624. Min Act: -0.0003

Data Index: 660733 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1577510 (Python Code)

Max Activating Token Index: 556

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0603. Min Act: -0.0003

Data Index: 239007 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1497576 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1505777 (Python Code)

Max Activating Token Index: 616

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1644559 (Python Code)

Max Activating Token Index: 481

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1158718 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0640. Min Act: -0.0003

Data Index: 1392441 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0632. Min Act: -0.0003

Data Index: 1313565 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1619655 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0611. Min Act: -0.0003

Data Index: 565505 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0597. Min Act: -0.0003

Data Index: 851629 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0573. Min Act: -0.0003

Data Index: 253749 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0643. Min Act: -0.0003

Data Index: 48506 (C4 (Web Text))

Max Activating Token Index: 269