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

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

Neuron 4054 in Layer 7

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: -0.0000

Data Index: 873315 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1001313 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0984. Min Act: -0.0000

Data Index: 86807 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0801. Min Act: -0.0000

Data Index: 592952 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0782. Min Act: -0.0000

Data Index: 144271 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0808. Min Act: -0.0000

Data Index: 513178 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1328208 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0821. Min Act: -0.0000

Data Index: 780134 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0750. Min Act: -0.0000

Data Index: 693035 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1619405 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0803. Min Act: -0.0000

Data Index: 430310 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0760. Min Act: -0.0000

Data Index: 767912 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1377878 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1308324 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1383737 (Python Code)

Max Activating Token Index: 577

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1135994 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0706. Min Act: -0.0000

Data Index: 682716 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0686. Min Act: -0.0000

Data Index: 967922 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0674. Min Act: -0.0000

Data Index: 34263 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0647. Min Act: -0.0000

Data Index: 888666 (C4 (Web Text))

Max Activating Token Index: 293