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

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

Neuron 2576 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.4112. Min Act: -0.0000

Data Index: 1026848 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.3545. Min Act: -0.0000

Data Index: 319277 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.0928. Min Act: -0.0000

Data Index: 506470 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.1959. Min Act: -0.0000

Data Index: 513531 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.0731. Min Act: -0.0000

Data Index: 212445 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 2.4112. Min Range: -2.4112

Max Act: 2.1719. Min Act: -0.0000

Data Index: 1241479 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.8841. Min Act: -0.0000

Data Index: 423235 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1118653 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.7866. Min Act: -0.0000

Data Index: 56476 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.6469. Min Act: -0.0000

Data Index: 232747 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.7813. Min Act: -0.0000

Data Index: 436514 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1194995 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.6714. Min Act: -0.0000

Data Index: 778444 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.6760. Min Act: -0.0000

Data Index: 68636 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.6915. Min Act: -0.0000

Data Index: 798907 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.7119. Min Act: -0.0000

Data Index: 620560 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.7372. Min Act: -0.0000

Data Index: 103272 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.8164. Min Act: -0.0000

Data Index: 157450 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.6068. Min Act: -0.0000

Data Index: 104326 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 2.4112. Min Range: -2.4112

Max Act: 1.5101. Min Act: -0.0000

Data Index: 1080723 (C4 (Web Text))

Max Activating Token Index: 207