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

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

Neuron 936 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4111. Min Act: -0.0002

Data Index: 1116098 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4394. Min Act: -0.0002

Data Index: 207183 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4592. Min Act: -0.0002

Data Index: 998557 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4018. Min Act: -0.0002

Data Index: 857554 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3854. Min Act: -0.0002

Data Index: 895424 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4148. Min Act: -0.0002

Data Index: 749972 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3882. Min Act: -0.0002

Data Index: 1113887 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4216. Min Act: -0.0002

Data Index: 500128 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4038. Min Act: -0.0002

Data Index: 962235 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3709. Min Act: -0.0002

Data Index: 1071907 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3823. Min Act: -0.0002

Data Index: 1235278 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3946. Min Act: -0.0002

Data Index: 679372 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3770. Min Act: -0.0002

Data Index: 590610 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3565. Min Act: -0.0002

Data Index: 10045 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3437. Min Act: -0.0002

Data Index: 698412 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3411. Min Act: -0.0002

Data Index: 294274 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3375. Min Act: -0.0002

Data Index: 822309 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3225. Min Act: -0.0002

Data Index: 273972 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3518. Min Act: -0.0002

Data Index: 756358 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3599. Min Act: -0.0002

Data Index: 64637 (C4 (Web Text))

Max Activating Token Index: 213