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

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

Neuron 77 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0876. Min Act: -0.0003

Data Index: 271739 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0834. Min Act: -0.0003

Data Index: 925132 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0811. Min Act: -0.0003

Data Index: 924064 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0811. Min Act: -0.0003

Data Index: 743012 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0792. Min Act: -0.0002

Data Index: 956695 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0757. Min Act: -0.0003

Data Index: 652435 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0693. Min Act: -0.0003

Data Index: 110532 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0715. Min Act: -0.0003

Data Index: 177393 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1190742 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1331473 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0679. Min Act: -0.0003

Data Index: 159428 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1130302 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0633. Min Act: -0.0003

Data Index: 70865 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1039188 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0672. Min Act: -0.0003

Data Index: 383350 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0648. Min Act: -0.0003

Data Index: 733065 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0668. Min Act: -0.0002

Data Index: 400407 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0693. Min Act: -0.0003

Data Index: 726532 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0645. Min Act: -0.0003

Data Index: 113085 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0604. Min Act: -0.0003

Data Index: 396576 (C4 (Web Text))

Max Activating Token Index: 193