Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 899 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1236907 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1118042 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0770. Min Act: -0.0002

Data Index: 67024 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1134826 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0744. Min Act: -0.0002

Data Index: 327613 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1106227 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0731. Min Act: -0.0002

Data Index: 446474 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1038081 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1079287 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1070421 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0736. Min Act: -0.0002

Data Index: 152456 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0725. Min Act: -0.0002

Data Index: 464416 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0670. Min Act: -0.0002

Data Index: 793739 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0731. Min Act: -0.0002

Data Index: 629879 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0683. Min Act: -0.0002

Data Index: 662812 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0725. Min Act: -0.0002

Data Index: 24079 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1193087 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0683. Min Act: -0.0002

Data Index: 693682 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0710. Min Act: -0.0002

Data Index: 182424 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1145882 (C4 (Web Text))

Max Activating Token Index: 179