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

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

Neuron 3884 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0869. Min Act: -0.0002

Data Index: 417383 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0817. Min Act: -0.0002

Data Index: 655261 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0736. Min Act: -0.0001

Data Index: 844598 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0734. Min Act: -0.0001

Data Index: 710599 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1215554 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1078539 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1072931 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0847. Min Act: -0.0002

Data Index: 382461 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0723. Min Act: -0.0002

Data Index: 705100 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0729. Min Act: -0.0002

Data Index: 56017 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0679. Min Act: -0.0002

Data Index: 953174 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0695. Min Act: -0.0001

Data Index: 191279 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0717. Min Act: -0.0002

Data Index: 852476 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0683. Min Act: -0.0002

Data Index: 159237 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0741. Min Act: -0.0002

Data Index: 116665 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0636. Min Act: -0.0001

Data Index: 834017 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1208355 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0726. Min Act: -0.0002

Data Index: 996698 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1353187 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0725. Min Act: -0.0001

Data Index: 52825 (C4 (Web Text))

Max Activating Token Index: 785