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

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

Neuron 582 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1618372 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1482608 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1525829 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1433042 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1436350 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1372632 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1593454 (Python Code)

Max Activating Token Index: 192

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1558844 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1576591 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1528228 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1377370 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1566233 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1463175 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1645729 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1370892 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1597625 (Python Code)

Max Activating Token Index: 164

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1524407 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1606289 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1398678 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1530459 (Python Code)

Max Activating Token Index: 276