Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 747 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0029. Min Act: -0.0005

Data Index: 1423950 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0029. Min Act: -0.0006

Data Index: 1582930 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0028. Min Act: -0.0006

Data Index: 1373038 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0027. Min Act: -0.0006

Data Index: 1570974 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0027. Min Act: -0.0006

Data Index: 1437316 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0026. Min Act: -0.0006

Data Index: 1388989 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0026. Min Act: -0.0005

Data Index: 1609983 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0026. Min Act: -0.0006

Data Index: 1463963 (Python Code)

Max Activating Token Index: 42

Text #8

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0026. Min Act: -0.0006

Data Index: 1576853 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0026. Min Act: -0.0005

Data Index: 1637005 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0026. Min Act: -0.0005

Data Index: 1372615 (Python Code)

Max Activating Token Index: 72

Text #11

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0026. Min Act: -0.0006

Data Index: 1445490 (Python Code)

Max Activating Token Index: 437

Text #12

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0026. Min Act: -0.0006

Data Index: 1439420 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0005

Data Index: 1526198 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 1584309 (Python Code)

Max Activating Token Index: 24

Text #15

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0005

Data Index: 1481822 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0005

Data Index: 1635571 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0005

Data Index: 1492295 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 1381692 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 0.0029. Min Range: -0.0029

Max Act: 0.0025. Min Act: -0.0006

Data Index: 1629413 (Python Code)

Max Activating Token Index: 27