Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1785 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1074184 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0003

Data Index: 884225 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1274604 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1205095 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0758. Min Act: -0.0003

Data Index: 96100 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0590. Min Act: -0.0003

Data Index: 358601 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0685. Min Act: -0.0003

Data Index: 51870 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0795. Min Act: -0.0003

Data Index: 44564 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0642. Min Act: -0.0003

Data Index: 166338 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0637. Min Act: -0.0003

Data Index: 246530 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0629. Min Act: -0.0003

Data Index: 544284 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0673. Min Act: -0.0003

Data Index: 66872 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0639. Min Act: -0.0003

Data Index: 60268 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0623. Min Act: -0.0003

Data Index: 620803 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0615. Min Act: -0.0003

Data Index: 453058 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0467. Min Act: -0.0003

Data Index: 88112 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1332528 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0550. Min Act: -0.0003

Data Index: 870754 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1158175 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0675. Min Act: -0.0003

Data Index: 963909 (C4 (Web Text))

Max Activating Token Index: 865