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

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

Neuron 894 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0005

Data Index: 987165 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0815. Min Act: -0.0005

Data Index: 41856 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0760. Min Act: -0.0005

Data Index: 144903 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0790. Min Act: -0.0005

Data Index: 342049 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0750. Min Act: -0.0005

Data Index: 498699 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0759. Min Act: -0.0005

Data Index: 712172 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0759. Min Act: -0.0005

Data Index: 523495 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0740. Min Act: -0.0005

Data Index: 62653 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0718. Min Act: -0.0005

Data Index: 1181506 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0750. Min Act: -0.0005

Data Index: 376405 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0733. Min Act: -0.0005

Data Index: 489914 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0720. Min Act: -0.0004

Data Index: 645102 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0736. Min Act: -0.0005

Data Index: 705732 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0720. Min Act: -0.0005

Data Index: 447138 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0669. Min Act: -0.0005

Data Index: 316836 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0730. Min Act: -0.0005

Data Index: 625982 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0711. Min Act: -0.0005

Data Index: 1242208 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0726. Min Act: -0.0005

Data Index: 609237 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0687. Min Act: -0.0005

Data Index: 448925 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0690. Min Act: -0.0005

Data Index: 13790 (C4 (Web Text))

Max Activating Token Index: 266