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

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

Neuron 2868 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: 0.3996. Min Range: -0.3996

Max Act: 0.3996. Min Act: -0.0001

Data Index: 1626900 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3867. Min Act: -0.0001

Data Index: 1596533 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1544484 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3817. Min Act: -0.0001

Data Index: 1485002 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3826. Min Act: -0.0001

Data Index: 1558953 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3701. Min Act: -0.0001

Data Index: 1409973 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3714. Min Act: -0.0001

Data Index: 1364823 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3652. Min Act: -0.0001

Data Index: 1562812 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3638. Min Act: -0.0001

Data Index: 1395808 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3655. Min Act: -0.0001

Data Index: 1430636 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3687. Min Act: -0.0001

Data Index: 1446819 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3626. Min Act: -0.0001

Data Index: 1648905 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3667. Min Act: -0.0002

Data Index: 1497430 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1447094 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1530785 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3573. Min Act: -0.0002

Data Index: 1501752 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3547. Min Act: -0.0001

Data Index: 1600705 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3640. Min Act: -0.0001

Data Index: 1370689 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3586. Min Act: -0.0001

Data Index: 1572113 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3535. Min Act: -0.0001

Data Index: 1581805 (Python Code)

Max Activating Token Index: 3