Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1700 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0877. Min Act: -0.0003

Data Index: 493950 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0846. Min Act: -0.0003

Data Index: 1350614 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0915. Min Act: -0.0003

Data Index: 191450 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0905. Min Act: -0.0003

Data Index: 587646 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0858. Min Act: -0.0003

Data Index: 679557 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0872. Min Act: -0.0003

Data Index: 1118640 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0842. Min Act: -0.0003

Data Index: 173971 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0897. Min Act: -0.0004

Data Index: 714802 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0812. Min Act: -0.0003

Data Index: 76818 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0808. Min Act: -0.0003

Data Index: 748201 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0857. Min Act: -0.0003

Data Index: 1006162 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1212904 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0821. Min Act: -0.0004

Data Index: 536282 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0847. Min Act: -0.0003

Data Index: 513420 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1273452 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0868. Min Act: -0.0003

Data Index: 882517 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0910. Min Act: -0.0003

Data Index: 484042 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0837. Min Act: -0.0003

Data Index: 300783 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0830. Min Act: -0.0003

Data Index: 870793 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0837. Min Act: -0.0003

Data Index: 1210269 (C4 (Web Text))

Max Activating Token Index: 391