Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 621 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0003

Data Index: 4874 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0987. Min Act: -0.0003

Data Index: 1467894 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0917. Min Act: -0.0003

Data Index: 1596339 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0943. Min Act: -0.0003

Data Index: 1500666 (Python Code)

Max Activating Token Index: 903

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0922. Min Act: -0.0003

Data Index: 1495302 (Python Code)

Max Activating Token Index: 1003

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0887. Min Act: -0.0003

Data Index: 913623 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1556327 (Python Code)

Max Activating Token Index: 801

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0901. Min Act: -0.0003

Data Index: 1594104 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0889. Min Act: -0.0003

Data Index: 1512556 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1535890 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0843. Min Act: -0.0003

Data Index: 623224 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0839. Min Act: -0.0003

Data Index: 1384768 (Python Code)

Max Activating Token Index: 911

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1374686 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0831. Min Act: -0.0003

Data Index: 276652 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0819. Min Act: -0.0003

Data Index: 1474765 (Python Code)

Max Activating Token Index: 977

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1606747 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0841. Min Act: -0.0003

Data Index: 1604694 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0843. Min Act: -0.0003

Data Index: 1580194 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0774. Min Act: -0.0003

Data Index: 1542358 (Python Code)

Max Activating Token Index: 510

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0771. Min Act: -0.0003

Data Index: 1410530 (Python Code)

Max Activating Token Index: 426