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

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

Neuron 1598 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2678. Min Act: -0.0001

Data Index: 1539051 (Python Code)

Max Activating Token Index: 744

Text #1

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1429983 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1394950 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2733. Min Act: -0.0001

Data Index: 1394263 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2549. Min Act: -0.0001

Data Index: 1376626 (Python Code)

Max Activating Token Index: 955

Text #5

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1426685 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1619951 (Python Code)

Max Activating Token Index: 809

Text #7

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1396919 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1571265 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1444396 (Python Code)

Max Activating Token Index: 712

Text #10

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1571544 (Python Code)

Max Activating Token Index: 720

Text #11

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1639728 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1616561 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1580046 (Python Code)

Max Activating Token Index: 869

Text #14

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1601724 (Python Code)

Max Activating Token Index: 442

Text #15

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2458. Min Act: -0.0001

Data Index: 1396498 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2808. Min Act: -0.0001

Data Index: 1419128 (Python Code)

Max Activating Token Index: 757

Text #17

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1413469 (Python Code)

Max Activating Token Index: 378

Text #18

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1640350 (Python Code)

Max Activating Token Index: 671

Text #19

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1376256 (Python Code)

Max Activating Token Index: 356