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

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

Neuron 3827 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1718. Min Act: -0.0002

Data Index: 1552411 (Python Code)

Max Activating Token Index: 548

Text #1

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1639043 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1533918 (Python Code)

Max Activating Token Index: 1020

Text #3

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1628609 (Python Code)

Max Activating Token Index: 653

Text #4

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1563350 (Python Code)

Max Activating Token Index: 904

Text #5

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1454870 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1596991 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1429143 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1470838 (Python Code)

Max Activating Token Index: 639

Text #9

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1389608 (Python Code)

Max Activating Token Index: 522

Text #10

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1419503 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1449219 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1635774 (Python Code)

Max Activating Token Index: 791

Text #13

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1607121 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1562340 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1487385 (Python Code)

Max Activating Token Index: 784

Text #16

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1465363 (Python Code)

Max Activating Token Index: 788

Text #17

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1654202 (Python Code)

Max Activating Token Index: 963

Text #18

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1409237 (Python Code)

Max Activating Token Index: 749

Text #19

Max Range: 0.1718. Min Range: -0.1718

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1546571 (Python Code)

Max Activating Token Index: 897