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

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

Neuron 3171 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1534997 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.3255. Min Act: -0.0000

Data Index: 871007 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1551339 (Python Code)

Max Activating Token Index: 900

Text #3

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2528. Min Act: -0.0001

Data Index: 1537566 (Python Code)

Max Activating Token Index: 467

Text #4

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2855. Min Act: -0.0000

Data Index: 583791 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2698. Min Act: -0.0000

Data Index: 650337 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1078871 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1606550 (Python Code)

Max Activating Token Index: 408

Text #8

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2657. Min Act: -0.0000

Data Index: 51169 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2611. Min Act: -0.0000

Data Index: 412625 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1044190 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2678. Min Act: -0.0000

Data Index: 14263 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1553763 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1547859 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2467. Min Act: -0.0000

Data Index: 812532 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2448. Min Act: -0.0000

Data Index: 481635 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1402623 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1061429 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2857. Min Act: -0.0000

Data Index: 1571260 (Python Code)

Max Activating Token Index: 419

Text #19

Max Range: 0.3578. Min Range: -0.3578

Max Act: 0.2469. Min Act: -0.0000

Data Index: 791979 (C4 (Web Text))

Max Activating Token Index: 584