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

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

Neuron 3671 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0003

Data Index: 830895 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0980. Min Act: -0.0002

Data Index: 362740 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0933. Min Act: -0.0002

Data Index: 890152 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0901. Min Act: -0.0003

Data Index: 31161 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0893. Min Act: -0.0003

Data Index: 1109843 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1083703 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0847. Min Act: -0.0003

Data Index: 181278 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1253558 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0860. Min Act: -0.0002

Data Index: 458642 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1268397 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0834. Min Act: -0.0002

Data Index: 413090 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0799. Min Act: -0.0003

Data Index: 224800 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0835. Min Act: -0.0002

Data Index: 10481 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0794. Min Act: -0.0003

Data Index: 574860 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0763. Min Act: -0.0003

Data Index: 865406 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0788. Min Act: -0.0003

Data Index: 18145 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0757. Min Act: -0.0002

Data Index: 420756 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0755. Min Act: -0.0002

Data Index: 293313 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0780. Min Act: -0.0002

Data Index: 205275 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0789. Min Act: -0.0002

Data Index: 179669 (C4 (Web Text))

Max Activating Token Index: 381