Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3743 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.2628. Min Range: -6.2628

Max Act: 6.2628. Min Act: -0.0000

Data Index: 1548415 (Python Code)

Max Activating Token Index: 724

Text #1

Max Range: 6.2628. Min Range: -6.2628

Max Act: 5.6156. Min Act: -0.0000

Data Index: 1604616 (Python Code)

Max Activating Token Index: 497

Text #2

Max Range: 6.2628. Min Range: -6.2628

Max Act: 5.4092. Min Act: -0.0000

Data Index: 1394122 (Python Code)

Max Activating Token Index: 175

Text #3

Max Range: 6.2628. Min Range: -6.2628

Max Act: 5.0998. Min Act: -0.0000

Data Index: 1597223 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 6.2628. Min Range: -6.2628

Max Act: 5.1022. Min Act: -0.0000

Data Index: 1436368 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 6.2628. Min Range: -6.2628

Max Act: 5.0173. Min Act: -0.0000

Data Index: 1364808 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.8211. Min Act: -0.0000

Data Index: 1466737 (Python Code)

Max Activating Token Index: 607

Text #7

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.9938. Min Act: -0.0000

Data Index: 1647308 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.8096. Min Act: -0.0000

Data Index: 1547218 (Python Code)

Max Activating Token Index: 930

Text #9

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.9799. Min Act: -0.0000

Data Index: 1534842 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.7099. Min Act: -0.0000

Data Index: 1475717 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.8577. Min Act: -0.0000

Data Index: 1654682 (Python Code)

Max Activating Token Index: 400

Text #12

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.7083. Min Act: -0.0000

Data Index: 1412922 (Python Code)

Max Activating Token Index: 948

Text #13

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.8022. Min Act: -0.0000

Data Index: 1597531 (Python Code)

Max Activating Token Index: 334

Text #14

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.7908. Min Act: -0.0000

Data Index: 1524798 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.8108. Min Act: -0.0000

Data Index: 1517082 (Python Code)

Max Activating Token Index: 345

Text #16

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.8154. Min Act: 0.0000

Data Index: 1601795 (Python Code)

Max Activating Token Index: 809

Text #17

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.7828. Min Act: -0.0000

Data Index: 1578872 (Python Code)

Max Activating Token Index: 397

Text #18

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.8816. Min Act: -0.0000

Data Index: 1379212 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 6.2628. Min Range: -6.2628

Max Act: 4.6633. Min Act: -0.0000

Data Index: 1603470 (Python Code)

Max Activating Token Index: 396