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

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

Neuron 1367 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9922. Min Act: -0.0000

Data Index: 415172 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.0757. Min Range: -1.0757

Max Act: 1.0024. Min Act: -0.0000

Data Index: 784962 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.0757. Min Range: -1.0757

Max Act: 1.0757. Min Act: -0.0000

Data Index: 540544 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1067724 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1036299 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8658. Min Act: -0.0000

Data Index: 299327 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9438. Min Act: -0.0000

Data Index: 446682 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8887. Min Act: -0.0000

Data Index: 366590 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1333940 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8029. Min Act: -0.0000

Data Index: 423842 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8125. Min Act: -0.0000

Data Index: 49371 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8402. Min Act: -0.0000

Data Index: 457110 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9375. Min Act: -0.0000

Data Index: 934697 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8378. Min Act: -0.0000

Data Index: 995908 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.7728. Min Act: -0.0000

Data Index: 40041 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1122858 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1269044 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9075. Min Act: -0.0000

Data Index: 78065 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9051. Min Act: -0.0000

Data Index: 263675 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8196. Min Act: -0.0000

Data Index: 911980 (C4 (Web Text))

Max Activating Token Index: 968