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

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

Neuron 1387 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.6394. Min Act: -0.0000

Data Index: 916283 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5820. Min Act: -0.0001

Data Index: 75747 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5631. Min Act: -0.0000

Data Index: 59577 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1403681 (Python Code)

Max Activating Token Index: 646

Text #4

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5043. Min Act: -0.0000

Data Index: 229425 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1170523 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1020062 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5010. Min Act: -0.0001

Data Index: 68659 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1075117 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5134. Min Act: -0.0000

Data Index: 394295 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4827. Min Act: -0.0001

Data Index: 818897 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5088. Min Act: -0.0000

Data Index: 476156 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4945. Min Act: -0.0000

Data Index: 113950 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4536. Min Act: -0.0000

Data Index: 21239 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4960. Min Act: -0.0000

Data Index: 227603 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1280069 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4808. Min Act: -0.0000

Data Index: 59878 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4846. Min Act: -0.0000

Data Index: 863563 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4627. Min Act: -0.0000

Data Index: 786575 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4792. Min Act: -0.0000

Data Index: 461317 (C4 (Web Text))

Max Activating Token Index: 993