Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 620 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.1393. Min Act: -0.1700

Data Index: 1460877 (Python Code)

Max Activating Token Index: 357

Text #1

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0763. Min Act: -0.1700

Data Index: 1474910 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0763. Min Act: -0.1700

Data Index: 1417989 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0763. Min Act: -0.1700

Data Index: 1446696 (Python Code)

Max Activating Token Index: 501

Text #4

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0605. Min Act: -0.1700

Data Index: 1388418 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0605. Min Act: -0.1700

Data Index: 1656590 (Python Code)

Max Activating Token Index: 28

Text #6

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1520274 (Python Code)

Max Activating Token Index: 933

Text #7

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0447. Min Act: -0.1700

Data Index: 1474097 (Python Code)

Max Activating Token Index: 376

Text #8

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0447. Min Act: -0.1700

Data Index: 1537336 (Python Code)

Max Activating Token Index: 496

Text #9

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0447. Min Act: -0.1700

Data Index: 1423587 (Python Code)

Max Activating Token Index: 796

Text #10

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1489903 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0447. Min Act: -0.1700

Data Index: 1633049 (Python Code)

Max Activating Token Index: 339

Text #12

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0447. Min Act: -0.1700

Data Index: 1634014 (Python Code)

Max Activating Token Index: 527

Text #13

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1369657 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1510968 (Python Code)

Max Activating Token Index: 70

Text #15

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0447. Min Act: -0.1700

Data Index: 1552330 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1592813 (Python Code)

Max Activating Token Index: 610

Text #17

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0447. Min Act: -0.1700

Data Index: 1582778 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1399999 (Python Code)

Max Activating Token Index: 799

Text #19

Max Range: 3.1393. Min Range: -3.1393

Max Act: 3.0131. Min Act: -0.1700

Data Index: 1513283 (Python Code)

Max Activating Token Index: 31