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

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

Neuron 4865 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1492803 (Python Code)

Max Activating Token Index: 923

Text #1

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.7533. Min Act: -0.0000

Data Index: 108780 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1478889 (Python Code)

Max Activating Token Index: 903

Text #3

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1524779 (Python Code)

Max Activating Token Index: 702

Text #4

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6590. Min Act: -0.0000

Data Index: 945442 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6230. Min Act: -0.0000

Data Index: 88583 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6091. Min Act: -0.0000

Data Index: 208461 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5866. Min Act: -0.0000

Data Index: 713589 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1522040 (Python Code)

Max Activating Token Index: 280

Text #9

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5927. Min Act: -0.0000

Data Index: 113296 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5314. Min Act: -0.0000

Data Index: 93232 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1021781 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1172122 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5579. Min Act: -0.0000

Data Index: 669074 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5660. Min Act: -0.0000

Data Index: 881446 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4669. Min Act: -0.0000

Data Index: 456452 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1192466 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5453. Min Act: -0.0000

Data Index: 67555 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5127. Min Act: -0.0000

Data Index: 748756 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5558. Min Act: -0.0000

Data Index: 149304 (C4 (Web Text))

Max Activating Token Index: 687