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

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

Neuron 4928 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: 1.8430. Min Range: -1.8430

Max Act: 1.8430. Min Act: -0.0000

Data Index: 1439529 (Python Code)

Max Activating Token Index: 890

Text #1

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.7980. Min Act: -0.0000

Data Index: 1461214 (Python Code)

Max Activating Token Index: 872

Text #2

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.6769. Min Act: -0.0000

Data Index: 1469263 (Python Code)

Max Activating Token Index: 662

Text #3

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1370887 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.6158. Min Act: -0.0000

Data Index: 1540758 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.5771. Min Act: -0.0001

Data Index: 1379506 (Python Code)

Max Activating Token Index: 816

Text #6

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1378460 (Python Code)

Max Activating Token Index: 762

Text #7

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.5672. Min Act: -0.0000

Data Index: 1484789 (Python Code)

Max Activating Token Index: 160

Text #8

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1413868 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4604. Min Act: -0.0000

Data Index: 1588483 (Python Code)

Max Activating Token Index: 1006

Text #10

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4949. Min Act: -0.0000

Data Index: 1563991 (Python Code)

Max Activating Token Index: 60

Text #11

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4981. Min Act: -0.0000

Data Index: 1530126 (Python Code)

Max Activating Token Index: 435

Text #12

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4623. Min Act: -0.0000

Data Index: 1640263 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3789. Min Act: -0.0000

Data Index: 1449328 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1567255 (Python Code)

Max Activating Token Index: 1015

Text #15

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1555973 (Python Code)

Max Activating Token Index: 790

Text #16

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.5879. Min Act: -0.0000

Data Index: 1630966 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1469806 (Python Code)

Max Activating Token Index: 550

Text #18

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.3704. Min Act: -0.0000

Data Index: 1365162 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 1.8430. Min Range: -1.8430

Max Act: 1.4529. Min Act: -0.0000

Data Index: 1458437 (Python Code)

Max Activating Token Index: 318