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

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

Neuron 5278 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: 0.1895. Min Range: -0.1895

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1602652 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1552246 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1545082 (Python Code)

Max Activating Token Index: 283

Text #3

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1632470 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1419118 (Python Code)

Max Activating Token Index: 134

Text #5

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1744. Min Act: -0.0002

Data Index: 1610517 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1740. Min Act: -0.0001

Data Index: 1568880 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1639434 (Python Code)

Max Activating Token Index: 54

Text #8

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1582224 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1554267 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1593945 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1647687 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1449626 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1575885 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1438308 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1522406 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1624978 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1509757 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1573. Min Act: -0.0002

Data Index: 1554937 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1543417 (Python Code)

Max Activating Token Index: 23