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

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

Neuron 3753 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1461585 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1634248 (Python Code)

Max Activating Token Index: 982

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1439106 (Python Code)

Max Activating Token Index: 949

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1568688 (Python Code)

Max Activating Token Index: 674

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1530842 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0827. Min Act: -0.0002

Data Index: 891566 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1527114 (Python Code)

Max Activating Token Index: 882

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1531872 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0780. Min Act: -0.0002

Data Index: 217808 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1511000 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1430504 (Python Code)

Max Activating Token Index: 353

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1656879 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1404423 (Python Code)

Max Activating Token Index: 172

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1615759 (Python Code)

Max Activating Token Index: 768

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1370152 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1390011 (Python Code)

Max Activating Token Index: 559

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1619379 (Python Code)

Max Activating Token Index: 935

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1456355 (Python Code)

Max Activating Token Index: 965

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1647754 (Python Code)

Max Activating Token Index: 279

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1111122 (C4 (Web Text))

Max Activating Token Index: 942