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

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

Neuron 2959 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.6144. Min Act: -0.0001

Data Index: 1622080 (Python Code)

Max Activating Token Index: 1011

Text #1

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.6591. Min Act: -0.0001

Data Index: 1595919 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1611228 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5796. Min Act: -0.0001

Data Index: 1651628 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1517944 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1580089 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1382994 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1478110 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1505689 (Python Code)

Max Activating Token Index: 582

Text #9

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1616336 (Python Code)

Max Activating Token Index: 871

Text #10

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1376202 (Python Code)

Max Activating Token Index: 660

Text #11

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1375087 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1408018 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1512539 (Python Code)

Max Activating Token Index: 151

Text #14

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5453. Min Act: -0.0001

Data Index: 1368270 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1622852 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1598267 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5401. Min Act: -0.0001

Data Index: 1461158 (Python Code)

Max Activating Token Index: 347

Text #18

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1539401 (Python Code)

Max Activating Token Index: 533

Text #19

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1631492 (Python Code)

Max Activating Token Index: 907