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

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

Neuron 915 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.1015. Min Act: -0.0003

Data Index: 1496151 (Python Code)

Max Activating Token Index: 780

Text #1

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0959. Min Act: -0.0003

Data Index: 1524166 (Python Code)

Max Activating Token Index: 154

Text #2

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0901. Min Act: -0.0003

Data Index: 1459099 (Python Code)

Max Activating Token Index: 642

Text #3

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0955. Min Act: -0.0003

Data Index: 1476912 (Python Code)

Max Activating Token Index: 449

Text #4

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0924. Min Act: -0.0003

Data Index: 1444883 (Python Code)

Max Activating Token Index: 649

Text #5

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0927. Min Act: -0.0003

Data Index: 1650630 (Python Code)

Max Activating Token Index: 347

Text #6

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0928. Min Act: -0.0003

Data Index: 1485833 (Python Code)

Max Activating Token Index: 166

Text #7

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0939. Min Act: -0.0003

Data Index: 1370194 (Python Code)

Max Activating Token Index: 74

Text #8

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0936. Min Act: -0.0003

Data Index: 1608101 (Python Code)

Max Activating Token Index: 413

Text #9

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0936. Min Act: -0.0003

Data Index: 1549979 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0928. Min Act: -0.0003

Data Index: 1479223 (Python Code)

Max Activating Token Index: 514

Text #11

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1489850 (Python Code)

Max Activating Token Index: 860

Text #12

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0912. Min Act: -0.0003

Data Index: 1412697 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0863. Min Act: -0.0003

Data Index: 1615861 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0876. Min Act: -0.0003

Data Index: 1574686 (Python Code)

Max Activating Token Index: 188

Text #15

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1410412 (Python Code)

Max Activating Token Index: 233

Text #16

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0914. Min Act: -0.0003

Data Index: 1558266 (Python Code)

Max Activating Token Index: 504

Text #17

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0849. Min Act: -0.0003

Data Index: 1523360 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0864. Min Act: -0.0003

Data Index: 1580742 (Python Code)

Max Activating Token Index: 254

Text #19

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0856. Min Act: -0.0003

Data Index: 1632201 (Python Code)

Max Activating Token Index: 577