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

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

Neuron 3623 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1360465 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0741. Min Act: -0.0002

Data Index: 907574 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0721. Min Act: -0.0002

Data Index: 344320 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1556732 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1216645 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0700. Min Act: -0.0002

Data Index: 971380 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0687. Min Act: -0.0002

Data Index: 948994 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1523740 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0677. Min Act: -0.0003

Data Index: 152359 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1579586 (Python Code)

Max Activating Token Index: 869

Text #10

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1426309 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1451984 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1494988 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1467416 (Python Code)

Max Activating Token Index: 95

Text #14

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1392198 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1245339 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1652365 (Python Code)

Max Activating Token Index: 49

Text #17

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1600761 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1554727 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1397723 (Python Code)

Max Activating Token Index: 49