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

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

Neuron 2735 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: 0.1997. Min Range: -0.1997

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1413965 (Python Code)

Max Activating Token Index: 54

Text #1

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1568295 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1565872 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1515594 (Python Code)

Max Activating Token Index: 184

Text #4

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1533693 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1612951 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1797. Min Act: -0.0001

Data Index: 1606733 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1615540 (Python Code)

Max Activating Token Index: 73

Text #8

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1671. Min Act: -0.0001

Data Index: 1485729 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1414005 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1430002 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1587519 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1631386 (Python Code)

Max Activating Token Index: 994

Text #13

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1590809 (Python Code)

Max Activating Token Index: 207

Text #14

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1477726 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1635110 (Python Code)

Max Activating Token Index: 48

Text #16

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1545526 (Python Code)

Max Activating Token Index: 128

Text #17

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1464063 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1408142 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 0.1997. Min Range: -0.1997

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1654551 (Python Code)

Max Activating Token Index: 300