Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 433 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1347998 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1574958 (Python Code)

Max Activating Token Index: 408

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0582. Min Act: -0.0003

Data Index: 125843 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0580. Min Act: -0.0003

Data Index: 396102 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0546. Min Act: -0.0002

Data Index: 58930 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1491132 (Python Code)

Max Activating Token Index: 391

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0506. Min Act: -0.0003

Data Index: 172135 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1125400 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1068301 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0502. Min Act: -0.0003

Data Index: 775919 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0524. Min Act: -0.0003

Data Index: 507263 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1556179 (Python Code)

Max Activating Token Index: 742

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1385823 (Python Code)

Max Activating Token Index: 366

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1002357 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1145362 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0508. Min Act: -0.0003

Data Index: 478870 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0507. Min Act: -0.0003

Data Index: 182324 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1532744 (Python Code)

Max Activating Token Index: 611

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0484. Min Act: -0.0003

Data Index: 468206 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0492. Min Act: -0.0003

Data Index: 974627 (C4 (Web Text))

Max Activating Token Index: 191