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

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

Neuron 5095 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1453333 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1366844 (Python Code)

Max Activating Token Index: 198

Text #2

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1501021 (Python Code)

Max Activating Token Index: 249

Text #3

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1511239 (Python Code)

Max Activating Token Index: 146

Text #4

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1456543 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1502553 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1511072 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1385143 (Python Code)

Max Activating Token Index: 168

Text #8

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1616908 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1646005 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1588296 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1600392 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1509135 (Python Code)

Max Activating Token Index: 356

Text #13

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1370743 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1644558 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1388430 (Python Code)

Max Activating Token Index: 130

Text #16

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1374143 (Python Code)

Max Activating Token Index: 997

Text #17

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1575319 (Python Code)

Max Activating Token Index: 243

Text #18

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1599856 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1553114 (Python Code)

Max Activating Token Index: 61