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

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

Neuron 1419 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.6381. Min Act: -0.0000

Data Index: 1449935 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.5961. Min Act: -0.0000

Data Index: 1546724 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4764. Min Act: -0.0000

Data Index: 1465630 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1427819 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1643645 (Python Code)

Max Activating Token Index: 58

Text #5

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1423101 (Python Code)

Max Activating Token Index: 260

Text #6

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1384623 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1641288 (Python Code)

Max Activating Token Index: 386

Text #8

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.1826. Min Act: -0.0000

Data Index: 1368562 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.1361. Min Act: -0.0000

Data Index: 1394666 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.1524. Min Act: -0.0000

Data Index: 1499689 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1380129 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 1.6381. Min Range: -1.6381

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1613602 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 1.6381. Min Range: -1.6381

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1385916 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 1.6381. Min Range: -1.6381

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1563890 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 1.6381. Min Range: -1.6381

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1576988 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 1.6381. Min Range: -1.6381

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1570443 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 1.6381. Min Range: -1.6381

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1482881 (Python Code)

Max Activating Token Index: 903

Text #18

Max Range: 1.6381. Min Range: -1.6381

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1519895 (Python Code)

Max Activating Token Index: 548

Text #19

Max Range: 1.6381. Min Range: -1.6381

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1523367 (Python Code)

Max Activating Token Index: 17