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

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

Neuron 3937 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.7976. Min Act: -0.0000

Data Index: 574442 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.9022. Min Act: -0.0000

Data Index: 16165 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.5062. Min Act: -0.0000

Data Index: 1342711 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.4376. Min Act: -0.0000

Data Index: 220241 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.2695. Min Act: -0.0000

Data Index: 956936 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.4016. Min Act: -0.0000

Data Index: 646320 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.1469. Min Act: -0.0000

Data Index: 426351 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.1825. Min Act: -0.0000

Data Index: 473003 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.3480. Min Act: -0.0000

Data Index: 190529 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.2799. Min Act: -0.0000

Data Index: 1034987 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.0147. Min Act: -0.0000

Data Index: 322134 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.1094. Min Act: -0.0000

Data Index: 1512495 (Python Code)

Max Activating Token Index: 1010

Text #12

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.2057. Min Act: -0.0000

Data Index: 357549 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.0807. Min Act: -0.0000

Data Index: 845809 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.2833. Min Act: -0.0000

Data Index: 794405 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 2.9022. Min Range: -2.9022

Max Act: 2.0750. Min Act: -0.0000

Data Index: 588255 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 2.9022. Min Range: -2.9022

Max Act: 1.9757. Min Act: -0.0000

Data Index: 458850 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 2.9022. Min Range: -2.9022

Max Act: 1.9779. Min Act: -0.0000

Data Index: 638715 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 2.9022. Min Range: -2.9022

Max Act: 1.9440. Min Act: -0.0000

Data Index: 1262370 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 2.9022. Min Range: -2.9022

Max Act: 1.9284. Min Act: -0.0000

Data Index: 368838 (C4 (Web Text))

Max Activating Token Index: 456