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

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

Neuron 3445 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1050776 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3468. Min Act: -0.0000

Data Index: 242687 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3510. Min Act: -0.0000

Data Index: 37080 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3394. Min Act: -0.0000

Data Index: 914427 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3273. Min Act: -0.0000

Data Index: 83445 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1378796 (Python Code)

Max Activating Token Index: 740

Text #6

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3061. Min Act: -0.0000

Data Index: 754960 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3060. Min Act: -0.0000

Data Index: 126183 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1275776 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1429275 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1524715 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.3185. Min Act: -0.0000

Data Index: 887248 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2764. Min Act: -0.0000

Data Index: 19084 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2634. Min Act: -0.0000

Data Index: 474748 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2902. Min Act: -0.0000

Data Index: 97556 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2742. Min Act: -0.0000

Data Index: 638158 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2779. Min Act: -0.0000

Data Index: 129148 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1447042 (Python Code)

Max Activating Token Index: 578

Text #18

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1624968 (Python Code)

Max Activating Token Index: 361

Text #19

Max Range: 0.3789. Min Range: -0.3789

Max Act: 0.2494. Min Act: -0.0000

Data Index: 769258 (C4 (Web Text))

Max Activating Token Index: 173