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

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

Neuron 1694 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: 0.6692. Min Range: -0.6692

Max Act: 0.6692. Min Act: -0.0000

Data Index: 35405 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1235487 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.6342. Min Act: -0.0000

Data Index: 466865 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5632. Min Act: -0.0000

Data Index: 87726 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5747. Min Act: -0.0000

Data Index: 223599 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5656. Min Act: -0.0000

Data Index: 704170 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.6038. Min Act: -0.0000

Data Index: 778198 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5125. Min Act: -0.0000

Data Index: 971117 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4873. Min Act: -0.0000

Data Index: 344709 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.6627. Min Act: -0.0000

Data Index: 306353 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4647. Min Act: -0.0000

Data Index: 517218 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.5049. Min Act: -0.0000

Data Index: 184877 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4851. Min Act: -0.0000

Data Index: 33461 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4750. Min Act: -0.0000

Data Index: 313753 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1315325 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1357108 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4631. Min Act: -0.0000

Data Index: 216948 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4586. Min Act: -0.0000

Data Index: 574206 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4674. Min Act: -0.0000

Data Index: 608295 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.6692. Min Range: -0.6692

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1027686 (C4 (Web Text))

Max Activating Token Index: 621