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

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

Neuron 812 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: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1429921 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1361960 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1565133 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1421293 (Python Code)

Max Activating Token Index: 18

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1376056 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1566656 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1521003 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1525068 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1409121 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1364541 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1641365 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1451591 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1624169 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1508650 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1625109 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1630992 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1598204 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1606006 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1495426 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1579876 (Python Code)

Max Activating Token Index: 28