Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1172 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1072. Min Act: -0.0001

Data Index: 219858 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1049. Min Act: -0.0001

Data Index: 359111 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1462855 (Python Code)

Max Activating Token Index: 980

Text #3

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1530188 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1385577 (Python Code)

Max Activating Token Index: 609

Text #5

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1422663 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0859. Min Act: -0.0001

Data Index: 90786 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1381574 (Python Code)

Max Activating Token Index: 621

Text #8

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0788. Min Act: -0.0001

Data Index: 964781 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0845. Min Act: -0.0001

Data Index: 772923 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0749. Min Act: -0.0001

Data Index: 673296 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1542784 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1589121 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1644455 (Python Code)

Max Activating Token Index: 116

Text #14

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1393221 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1535028 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0808. Min Act: -0.0001

Data Index: 748589 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1597698 (Python Code)

Max Activating Token Index: 825

Text #18

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0801. Min Act: -0.0001

Data Index: 857680 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1618520 (Python Code)

Max Activating Token Index: 980