Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 492 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.3616. Min Act: -0.0000

Data Index: 1490263 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 3.3616. Min Range: -3.3616

Max Act: 3.0452. Min Act: -0.0000

Data Index: 1609425 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.9321. Min Act: -0.0000

Data Index: 1589921 (Python Code)

Max Activating Token Index: 584

Text #3

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.7612. Min Act: -0.0000

Data Index: 1482006 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.6716. Min Act: -0.0000

Data Index: 1466484 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.6082. Min Act: -0.0000

Data Index: 1413811 (Python Code)

Max Activating Token Index: 934

Text #6

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.2626. Min Act: -0.0000

Data Index: 1459338 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.2819. Min Act: -0.0000

Data Index: 1635743 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.2719. Min Act: -0.0000

Data Index: 1580884 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.2256. Min Act: -0.0000

Data Index: 1380073 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.2203. Min Act: -0.0000

Data Index: 1499200 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.2029. Min Act: -0.0000

Data Index: 1616902 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.2089. Min Act: -0.0000

Data Index: 1429603 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.3059. Min Act: -0.0000

Data Index: 1469446 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.1566. Min Act: -0.0001

Data Index: 1630779 (Python Code)

Max Activating Token Index: 305

Text #15

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.1348. Min Act: -0.0000

Data Index: 1588073 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.0103. Min Act: -0.0000

Data Index: 1589998 (Python Code)

Max Activating Token Index: 68

Text #17

Max Range: 3.3616. Min Range: -3.3616

Max Act: 1.9859. Min Act: -0.0000

Data Index: 1521462 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.1012. Min Act: -0.0000

Data Index: 1386785 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 3.3616. Min Range: -3.3616

Max Act: 2.0945. Min Act: -0.0000

Data Index: 1400242 (Python Code)

Max Activating Token Index: 920