Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2420 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1138331 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0811. Min Act: -0.0002

Data Index: 283467 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0833. Min Act: -0.0002

Data Index: 838243 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1028682 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1292818 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0840. Min Act: -0.0002

Data Index: 248475 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1123818 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0798. Min Act: -0.0002

Data Index: 231507 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0770. Min Act: -0.0002

Data Index: 8193 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0764. Min Act: -0.0002

Data Index: 565382 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0752. Min Act: -0.0002

Data Index: 791979 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1214555 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1483129 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0736. Min Act: -0.0002

Data Index: 565829 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0701. Min Act: -0.0002

Data Index: 377101 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0706. Min Act: -0.0002

Data Index: 825827 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0725. Min Act: -0.0002

Data Index: 602305 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1453114 (Python Code)

Max Activating Token Index: 552

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0716. Min Act: -0.0002

Data Index: 389377 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0687. Min Act: -0.0002

Data Index: 599592 (C4 (Web Text))

Max Activating Token Index: 260