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

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

Neuron 1703 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1562513 (Python Code)

Max Activating Token Index: 628

Text #1

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1481760 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1392866 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1483829 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1610418 (Python Code)

Max Activating Token Index: 1008

Text #5

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1609341 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1032252 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1589393 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1591086 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1388284 (Python Code)

Max Activating Token Index: 808

Text #10

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1459347 (Python Code)

Max Activating Token Index: 651

Text #11

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1446399 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1484751 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1028251 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1585743 (Python Code)

Max Activating Token Index: 771

Text #15

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1561491 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1630919 (Python Code)

Max Activating Token Index: 662

Text #17

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0670. Min Act: -0.0001

Data Index: 618999 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1611819 (Python Code)

Max Activating Token Index: 798

Text #19

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1547355 (Python Code)

Max Activating Token Index: 72