Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1413 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1477785 (Python Code)

Max Activating Token Index: 987

Text #1

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1431977 (Python Code)

Max Activating Token Index: 146

Text #2

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0830. Min Act: -0.0003

Data Index: 1443500 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1466861 (Python Code)

Max Activating Token Index: 876

Text #4

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1507544 (Python Code)

Max Activating Token Index: 262

Text #5

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1566431 (Python Code)

Max Activating Token Index: 943

Text #6

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1548663 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1610251 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1367092 (Python Code)

Max Activating Token Index: 955

Text #9

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1491511 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1465798 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1467321 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1482450 (Python Code)

Max Activating Token Index: 211

Text #13

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1616814 (Python Code)

Max Activating Token Index: 728

Text #14

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1540276 (Python Code)

Max Activating Token Index: 194

Text #15

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1538046 (Python Code)

Max Activating Token Index: 345

Text #16

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0672. Min Act: -0.0004

Data Index: 1643691 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1640194 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0713. Min Act: -0.0003

Data Index: 1464401 (Python Code)

Max Activating Token Index: 100

Text #19

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1383971 (Python Code)

Max Activating Token Index: 778