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

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

Neuron 825 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.1964. Min Act: -0.0000

Data Index: 1497551 (Python Code)

Max Activating Token Index: 680

Text #1

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.1708. Min Act: -0.0000

Data Index: 1623488 (Python Code)

Max Activating Token Index: 872

Text #2

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0863. Min Act: -0.0000

Data Index: 1596994 (Python Code)

Max Activating Token Index: 289

Text #3

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.2926. Min Act: -0.0000

Data Index: 1369993 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.2848. Min Act: -0.0000

Data Index: 1575367 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.2794. Min Act: -0.0000

Data Index: 1504053 (Python Code)

Max Activating Token Index: 596

Text #6

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.2348. Min Act: -0.0000

Data Index: 1513680 (Python Code)

Max Activating Token Index: 728

Text #7

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0523. Min Act: -0.0000

Data Index: 1527576 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0090. Min Act: -0.0000

Data Index: 1468896 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0657. Min Act: -0.0000

Data Index: 1454292 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0619. Min Act: -0.0000

Data Index: 1586984 (Python Code)

Max Activating Token Index: 606

Text #11

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0293. Min Act: -0.0000

Data Index: 1592398 (Python Code)

Max Activating Token Index: 806

Text #12

Max Range: 4.2926. Min Range: -4.2926

Max Act: 3.8794. Min Act: -0.0000

Data Index: 1386398 (Python Code)

Max Activating Token Index: 636

Text #13

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.2111. Min Act: -0.0000

Data Index: 1600721 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0499. Min Act: -0.0000

Data Index: 1464947 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0375. Min Act: -0.0000

Data Index: 1619361 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0325. Min Act: -0.0000

Data Index: 1365832 (Python Code)

Max Activating Token Index: 712

Text #17

Max Range: 4.2926. Min Range: -4.2926

Max Act: 3.8383. Min Act: -0.0000

Data Index: 1476604 (Python Code)

Max Activating Token Index: 919

Text #18

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.1875. Min Act: -0.0000

Data Index: 1585172 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 4.2926. Min Range: -4.2926

Max Act: 3.8432. Min Act: -0.0000

Data Index: 1525019 (Python Code)

Max Activating Token Index: 621