Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 858 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1604931 (Python Code)

Max Activating Token Index: 992

Text #1

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0747. Min Act: -0.0000

Data Index: 158964 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0670. Min Act: -0.0000

Data Index: 412499 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0611. Min Act: -0.0000

Data Index: 916629 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0608. Min Act: -0.0000

Data Index: 936146 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0628. Min Act: -0.0000

Data Index: 233653 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0584. Min Act: -0.0000

Data Index: 119635 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1305229 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0611. Min Act: -0.0000

Data Index: 50141 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1021922 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1274704 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0552. Min Act: -0.0000

Data Index: 150478 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0540. Min Act: -0.0000

Data Index: 295621 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0520. Min Act: -0.0000

Data Index: 321713 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0519. Min Act: -0.0000

Data Index: 478496 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1440480 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0526. Min Act: -0.0000

Data Index: 737063 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0538. Min Act: -0.0000

Data Index: 868157 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0495. Min Act: -0.0000

Data Index: 500509 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0498. Min Act: -0.0000

Data Index: 265878 (C4 (Web Text))

Max Activating Token Index: 363