Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3630 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1211478 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1529625 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1528642 (Python Code)

Max Activating Token Index: 807

Text #3

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1545006 (Python Code)

Max Activating Token Index: 131

Text #4

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1521095 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1627093 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1478621 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1465089 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1623338 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1086323 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0917. Min Act: -0.0001

Data Index: 743661 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1445678 (Python Code)

Max Activating Token Index: 345

Text #12

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1449994 (Python Code)

Max Activating Token Index: 103

Text #13

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1390751 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0902. Min Act: -0.0001

Data Index: 660325 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1364776 (Python Code)

Max Activating Token Index: 678

Text #16

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1371584 (Python Code)

Max Activating Token Index: 242

Text #17

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1557111 (Python Code)

Max Activating Token Index: 637

Text #18

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1511019 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0794. Min Act: -0.0001

Data Index: 660411 (C4 (Web Text))

Max Activating Token Index: 894