Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3929 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.3590. Min Range: -6.3590

Max Act: 6.0584. Min Act: -0.0000

Data Index: 738787 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 6.3590. Min Range: -6.3590

Max Act: 6.3590. Min Act: -0.0000

Data Index: 321786 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.4855. Min Act: -0.0000

Data Index: 873735 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.7055. Min Act: -0.0000

Data Index: 847943 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.5623. Min Act: -0.0000

Data Index: 55712 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.3748. Min Act: -0.0000

Data Index: 388360 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.5424. Min Act: -0.0000

Data Index: 793540 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.4981. Min Act: -0.0000

Data Index: 27469 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.4518. Min Act: -0.0000

Data Index: 853493 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 6.3590. Min Range: -6.3590

Max Act: 4.7355. Min Act: -0.0000

Data Index: 551566 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.7156. Min Act: -0.0000

Data Index: 779133 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.1862. Min Act: -0.0000

Data Index: 649388 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.5008. Min Act: -0.0000

Data Index: 308193 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 6.3590. Min Range: -6.3590

Max Act: 4.9015. Min Act: -0.0000

Data Index: 709561 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.2524. Min Act: -0.0000

Data Index: 974679 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.0399. Min Act: -0.0000

Data Index: 1013910 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 6.3590. Min Range: -6.3590

Max Act: 4.8720. Min Act: -0.0000

Data Index: 1231127 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.2203. Min Act: -0.0000

Data Index: 842134 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.1849. Min Act: -0.0000

Data Index: 255584 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 6.3590. Min Range: -6.3590

Max Act: 5.3726. Min Act: -0.0000

Data Index: 1049053 (C4 (Web Text))

Max Activating Token Index: 635