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

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

Neuron 837 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0000

Data Index: 423829 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1598876 (Python Code)

Max Activating Token Index: 913

Text #2

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1481938 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1426570 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0589. Min Act: -0.0000

Data Index: 289939 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0601. Min Act: -0.0001

Data Index: 68188 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1642080 (Python Code)

Max Activating Token Index: 668

Text #7

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0550. Min Act: 0.0000

Data Index: 671270 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1591822 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0534. Min Act: -0.0001

Data Index: 281391 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0558. Min Act: -0.0001

Data Index: 640583 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1648746 (Python Code)

Max Activating Token Index: 406

Text #12

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1612881 (Python Code)

Max Activating Token Index: 690

Text #13

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0494. Min Act: -0.0002

Data Index: 781642 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1373244 (Python Code)

Max Activating Token Index: 731

Text #15

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1504689 (Python Code)

Max Activating Token Index: 502

Text #16

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1467028 (Python Code)

Max Activating Token Index: 494

Text #17

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0495. Min Act: -0.0001

Data Index: 124366 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1632561 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1571863 (Python Code)

Max Activating Token Index: 59