Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3107 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2377. Min Act: -0.0002

Data Index: 1372355 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.2043. Min Act: -0.0002

Data Index: 1613564 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1791. Min Act: -0.0002

Data Index: 1639482 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1733. Min Act: -0.0002

Data Index: 1536704 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1783. Min Act: -0.0002

Data Index: 1583106 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1619. Min Act: -0.0002

Data Index: 1618633 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1580. Min Act: -0.0002

Data Index: 1511885 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1641. Min Act: -0.0002

Data Index: 1591287 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1652. Min Act: -0.0002

Data Index: 1542039 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1477. Min Act: -0.0002

Data Index: 1376392 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1608. Min Act: -0.0002

Data Index: 1604322 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1450. Min Act: -0.0002

Data Index: 1487397 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1533. Min Act: -0.0002

Data Index: 1632963 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1475. Min Act: -0.0002

Data Index: 1374536 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1460. Min Act: -0.0002

Data Index: 1428825 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1554. Min Act: -0.0002

Data Index: 1377629 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1611. Min Act: -0.0002

Data Index: 1469462 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1495. Min Act: -0.0002

Data Index: 1573553 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1484. Min Act: -0.0002

Data Index: 1590645 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.2377. Min Range: -0.2377

Max Act: 0.1463. Min Act: -0.0002

Data Index: 1368680 (Python Code)

Max Activating Token Index: 17