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

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

Neuron 5784 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1491773 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1504833 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1410780 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1410687 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1446635 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1578527 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1501642 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1361648 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1369683 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1537433 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1479648 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1704. Min Act: -0.0002

Data Index: 1411742 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1642. Min Act: -0.0002

Data Index: 1600157 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1610. Min Act: -0.0002

Data Index: 1459625 (Python Code)

Max Activating Token Index: 2

Text #14

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1583. Min Act: -0.0002

Data Index: 1595156 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1546. Min Act: -0.0002

Data Index: 1411366 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1543. Min Act: -0.0002

Data Index: 1440172 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1544. Min Act: -0.0002

Data Index: 1545363 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1520. Min Act: -0.0002

Data Index: 1373919 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1510. Min Act: -0.0002

Data Index: 1395828 (Python Code)

Max Activating Token Index: 562