Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4242 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1484997 (Python Code)

Max Activating Token Index: 510

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1627606 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1534630 (Python Code)

Max Activating Token Index: 491

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1503636 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1455871 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1566904 (Python Code)

Max Activating Token Index: 737

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1420411 (Python Code)

Max Activating Token Index: 187

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1527710 (Python Code)

Max Activating Token Index: 579

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1562692 (Python Code)

Max Activating Token Index: 530

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1388163 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1390482 (Python Code)

Max Activating Token Index: 653

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1512011 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1500655 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1484410 (Python Code)

Max Activating Token Index: 728

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1513543 (Python Code)

Max Activating Token Index: 314

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1544104 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1493272 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1596500 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1601376 (Python Code)

Max Activating Token Index: 302

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1640998 (Python Code)

Max Activating Token Index: 782