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

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

Neuron 5198 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.4662. Min Act: 0.0000

Data Index: 1426621 (Python Code)

Max Activating Token Index: 987

Text #1

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.4203. Min Act: -0.0000

Data Index: 1526011 (Python Code)

Max Activating Token Index: 132

Text #2

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.3998. Min Act: -0.0000

Data Index: 1425000 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1542643 (Python Code)

Max Activating Token Index: 885

Text #4

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.3456. Min Act: -0.0000

Data Index: 1533204 (Python Code)

Max Activating Token Index: 900

Text #5

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2759. Min Act: -0.0000

Data Index: 1587438 (Python Code)

Max Activating Token Index: 872

Text #6

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2709. Min Act: 0.0000

Data Index: 1451536 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.3291. Min Act: -0.0000

Data Index: 1499379 (Python Code)

Max Activating Token Index: 433

Text #8

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2471. Min Act: -0.0000

Data Index: 1429118 (Python Code)

Max Activating Token Index: 665

Text #9

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1546388 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2414. Min Act: 0.0000

Data Index: 1391037 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1496977 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.3905. Min Act: 0.0000

Data Index: 1390857 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2984. Min Act: -0.0000

Data Index: 1472301 (Python Code)

Max Activating Token Index: 653

Text #14

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1578477 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2638. Min Act: 0.0000

Data Index: 1566443 (Python Code)

Max Activating Token Index: 546

Text #16

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2463. Min Act: 0.0000

Data Index: 1604117 (Python Code)

Max Activating Token Index: 390

Text #17

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.1563. Min Act: 0.0000

Data Index: 1524679 (Python Code)

Max Activating Token Index: 853

Text #18

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.2265. Min Act: -0.0000

Data Index: 1433625 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 1.4662. Min Range: -1.4662

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1533263 (Python Code)

Max Activating Token Index: 396