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

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

Neuron 2339 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: 0.0718. Min Range: -0.0718

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1424243 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1536626 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1555535 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1446428 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1446593 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1434495 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1507806 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1466775 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1509784 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1436167 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1569208 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1580569 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1435748 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1530705 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1465810 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1570491 (Python Code)

Max Activating Token Index: 134

Text #16

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1647098 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1463235 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1475220 (Python Code)

Max Activating Token Index: 299

Text #19

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1365318 (Python Code)

Max Activating Token Index: 72