Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2969 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1722. Min Range: -4.1722

Max Act: 4.1722. Min Act: -0.0001

Data Index: 1591718 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.6711. Min Act: -0.0001

Data Index: 1501417 (Python Code)

Max Activating Token Index: 59

Text #2

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.5055. Min Act: -0.0001

Data Index: 1638778 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.4917. Min Act: -0.0001

Data Index: 1561431 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 4.1722. Min Range: -4.1722

Max Act: 2.9767. Min Act: -0.0001

Data Index: 1580574 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.2498. Min Act: -0.0001

Data Index: 1628812 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.3937. Min Act: -0.0001

Data Index: 1636221 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.5249. Min Act: -0.0001

Data Index: 1420466 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.4370. Min Act: -0.0001

Data Index: 1529582 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 4.1722. Min Range: -4.1722

Max Act: 2.9654. Min Act: -0.0001

Data Index: 1647626 (Python Code)

Max Activating Token Index: 68

Text #10

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.3856. Min Act: -0.0001

Data Index: 1413853 (Python Code)

Max Activating Token Index: 122

Text #11

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.5557. Min Act: -0.0001

Data Index: 1431171 (Python Code)

Max Activating Token Index: 111

Text #12

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.5459. Min Act: -0.0001

Data Index: 1360657 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 4.1722. Min Range: -4.1722

Max Act: 2.9702. Min Act: -0.0001

Data Index: 1465582 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.2658. Min Act: -0.0001

Data Index: 1479845 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.0927. Min Act: -0.0001

Data Index: 1551129 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.2434. Min Act: -0.0001

Data Index: 1491300 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.0625. Min Act: -0.0001

Data Index: 1475561 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 4.1722. Min Range: -4.1722

Max Act: 3.0774. Min Act: -0.0001

Data Index: 1413821 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 4.1722. Min Range: -4.1722

Max Act: 2.9284. Min Act: -0.0001

Data Index: 1438000 (Python Code)

Max Activating Token Index: 109