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

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

Neuron 66 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1641735 (Python Code)

Max Activating Token Index: 203

Text #1

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1433962 (Python Code)

Max Activating Token Index: 115

Text #2

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1459718 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1409960 (Python Code)

Max Activating Token Index: 352

Text #4

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6033. Min Act: -0.0001

Data Index: 1435195 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1443612 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1458977 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5604. Min Act: -0.0001

Data Index: 1505901 (Python Code)

Max Activating Token Index: 229

Text #8

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1381732 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1655390 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1549623 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5722. Min Act: -0.0000

Data Index: 1438765 (Python Code)

Max Activating Token Index: 493

Text #12

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1522552 (Python Code)

Max Activating Token Index: 721

Text #13

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1477317 (Python Code)

Max Activating Token Index: 121

Text #14

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1585400 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1568084 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1526435 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1378709 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1532292 (Python Code)

Max Activating Token Index: 168

Text #19

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1435093 (Python Code)

Max Activating Token Index: 103