Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2677 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6366. Min Act: -0.0003

Data Index: 1410767 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6326. Min Act: -0.0003

Data Index: 1538380 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6314. Min Act: -0.0003

Data Index: 1507644 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6235. Min Act: -0.0003

Data Index: 1496834 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6111. Min Act: -0.0003

Data Index: 1533709 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6129. Min Act: -0.0003

Data Index: 1533884 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5814. Min Act: -0.0003

Data Index: 1562798 (Python Code)

Max Activating Token Index: 863

Text #7

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5984. Min Act: -0.0003

Data Index: 1428999 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5778. Min Act: -0.0003

Data Index: 1602909 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5718. Min Act: -0.0004

Data Index: 1550894 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5768. Min Act: -0.0003

Data Index: 1513038 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5767. Min Act: -0.0003

Data Index: 1431496 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5687. Min Act: -0.0003

Data Index: 1392130 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5875. Min Act: -0.0003

Data Index: 1589737 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5633. Min Act: -0.0003

Data Index: 1452354 (Python Code)

Max Activating Token Index: 840

Text #15

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5440. Min Act: -0.0003

Data Index: 1584060 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5539. Min Act: -0.0003

Data Index: 1613517 (Python Code)

Max Activating Token Index: 134

Text #17

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5318. Min Act: -0.0004

Data Index: 1626762 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5465. Min Act: -0.0003

Data Index: 1626794 (Python Code)

Max Activating Token Index: 193

Text #19

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5432. Min Act: -0.0003

Data Index: 1479342 (Python Code)

Max Activating Token Index: 121