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

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

Neuron 4666 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 200774 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0857. Min Act: -0.0002

Data Index: 630322 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0822. Min Act: -0.0002

Data Index: 734902 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0757. Min Act: -0.0002

Data Index: 197894 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0785. Min Act: -0.0002

Data Index: 204563 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0751. Min Act: -0.0002

Data Index: 122124 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1056142 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0755. Min Act: -0.0002

Data Index: 968332 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0777. Min Act: -0.0002

Data Index: 731090 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0680. Min Act: -0.0002

Data Index: 905256 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0673. Min Act: -0.0002

Data Index: 84706 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0758. Min Act: -0.0002

Data Index: 135141 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0722. Min Act: -0.0002

Data Index: 46126 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1329184 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0742. Min Act: -0.0002

Data Index: 968591 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0716. Min Act: -0.0002

Data Index: 195531 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0705. Min Act: -0.0002

Data Index: 358421 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1288429 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0719. Min Act: -0.0002

Data Index: 113805 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0672. Min Act: -0.0002

Data Index: 340585 (C4 (Web Text))

Max Activating Token Index: 309