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

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

Neuron 4693 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1293787 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1221693 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6604. Min Act: -0.0000

Data Index: 322676 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5655. Min Act: -0.0000

Data Index: 656183 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1063407 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5090. Min Act: -0.0000

Data Index: 678232 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5466. Min Act: -0.0000

Data Index: 936235 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4880. Min Act: -0.0000

Data Index: 543252 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4217. Min Act: -0.0000

Data Index: 975706 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4346. Min Act: -0.0000

Data Index: 92547 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4088. Min Act: -0.0000

Data Index: 738710 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3870. Min Act: -0.0000

Data Index: 867 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3902. Min Act: -0.0000

Data Index: 398784 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3892. Min Act: -0.0000

Data Index: 348206 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3975. Min Act: -0.0000

Data Index: 16664 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3938. Min Act: -0.0000

Data Index: 268210 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1285143 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1177939 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3438. Min Act: -0.0000

Data Index: 82576 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.3754. Min Act: -0.0000

Data Index: 740770 (C4 (Web Text))

Max Activating Token Index: 568