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

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

Neuron 2452 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2715. Min Range: -1.2715

Max Act: 1.2715. Min Act: -0.0000

Data Index: 1450298 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 1.2715. Min Range: -1.2715

Max Act: 1.1722. Min Act: -0.0000

Data Index: 141847 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 1.2715. Min Range: -1.2715

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1618456 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 1.2715. Min Range: -1.2715

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1518543 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 1.2715. Min Range: -1.2715

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1514450 (Python Code)

Max Activating Token Index: 237

Text #5

Max Range: 1.2715. Min Range: -1.2715

Max Act: 1.1377. Min Act: -0.0000

Data Index: 319230 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 1.2715. Min Range: -1.2715

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1634504 (Python Code)

Max Activating Token Index: 519

Text #7

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1413661 (Python Code)

Max Activating Token Index: 789

Text #8

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.9560. Min Act: -0.0000

Data Index: 576818 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1088740 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1486833 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.9627. Min Act: -0.0000

Data Index: 829478 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1521948 (Python Code)

Max Activating Token Index: 984

Text #13

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1647603 (Python Code)

Max Activating Token Index: 179

Text #14

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1631558 (Python Code)

Max Activating Token Index: 710

Text #15

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.8886. Min Act: -0.0000

Data Index: 845357 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1651419 (Python Code)

Max Activating Token Index: 673

Text #17

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1635625 (Python Code)

Max Activating Token Index: 382

Text #18

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1458815 (Python Code)

Max Activating Token Index: 397

Text #19

Max Range: 1.2715. Min Range: -1.2715

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1547011 (Python Code)

Max Activating Token Index: 611