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

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

Neuron 688 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0002

Data Index: 309792 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0606. Min Act: -0.0002

Data Index: 568193 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0587. Min Act: -0.0002

Data Index: 271215 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1242077 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0568. Min Act: -0.0002

Data Index: 735551 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0561. Min Act: -0.0002

Data Index: 430981 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1054839 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0556. Min Act: -0.0002

Data Index: 852414 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0540. Min Act: -0.0002

Data Index: 704489 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1534539 (Python Code)

Max Activating Token Index: 666

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1464284 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1650454 (Python Code)

Max Activating Token Index: 739

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1374360 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0510. Min Act: -0.0003

Data Index: 658862 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1193153 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0513. Min Act: -0.0002

Data Index: 514565 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1454669 (Python Code)

Max Activating Token Index: 276

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0507. Min Act: -0.0002

Data Index: 617088 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0495. Min Act: -0.0002

Data Index: 674440 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0502. Min Act: -0.0002

Data Index: 206312 (C4 (Web Text))

Max Activating Token Index: 261