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

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

Neuron 2391 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.4407. Min Act: -0.0000

Data Index: 618020 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.4005. Min Act: -0.0000

Data Index: 833996 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3602. Min Act: -0.0000

Data Index: 273028 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1354484 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3374. Min Act: -0.0000

Data Index: 122405 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2960. Min Act: -0.0000

Data Index: 38969 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2938. Min Act: -0.0000

Data Index: 436444 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3049. Min Act: -0.0000

Data Index: 632864 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2934. Min Act: 0.0001

Data Index: 1155199 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.3028. Min Act: -0.0000

Data Index: 126425 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1623762 (Python Code)

Max Activating Token Index: 939

Text #11

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2804. Min Act: -0.0000

Data Index: 743373 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2865. Min Act: -0.0000

Data Index: 431557 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1513027 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2873. Min Act: 0.0002

Data Index: 785911 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1320191 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2660. Min Act: -0.0000

Data Index: 470446 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1515103 (Python Code)

Max Activating Token Index: 181

Text #18

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1414736 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 0.4407. Min Range: -0.4407

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1613549 (Python Code)

Max Activating Token Index: 702