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

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

Neuron 495 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: 0.1425. Min Range: -0.1425

Max Act: 0.1425. Min Act: -0.0002

Data Index: 1496956 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1068. Min Act: -0.0002

Data Index: 182106 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1118. Min Act: -0.0002

Data Index: 1656792 (Python Code)

Max Activating Token Index: 566

Text #3

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1040. Min Act: -0.0002

Data Index: 696579 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1068272 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0935. Min Act: -0.0002

Data Index: 308985 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1656634 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1476216 (Python Code)

Max Activating Token Index: 289

Text #8

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1522798 (Python Code)

Max Activating Token Index: 572

Text #9

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1557638 (Python Code)

Max Activating Token Index: 962

Text #10

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1528641 (Python Code)

Max Activating Token Index: 55

Text #11

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1592781 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0799. Min Act: -0.0002

Data Index: 959814 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0800. Min Act: -0.0002

Data Index: 504734 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1593527 (Python Code)

Max Activating Token Index: 724

Text #15

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0802. Min Act: -0.0002

Data Index: 105681 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1527643 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1474345 (Python Code)

Max Activating Token Index: 233

Text #18

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1531295 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1399222 (Python Code)

Max Activating Token Index: 771