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

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

Neuron 3443 in Layer 0

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: 0.0769. Min Range: -0.0769

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1436134 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1610551 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1461081 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1648977 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1410044 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1481826 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1471224 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1442624 (Python Code)

Max Activating Token Index: 79

Text #8

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1527654 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1468113 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1411354 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1369744 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1503611 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1582615 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1563853 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1385655 (Python Code)

Max Activating Token Index: 50

Text #16

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1552433 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1629558 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1580530 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1429605 (Python Code)

Max Activating Token Index: 43