Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3715 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0579. Min Act: -0.0000

Data Index: 277667 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0654. Min Act: -0.0000

Data Index: 337935 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0695. Min Act: -0.0000

Data Index: 203950 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0576. Min Act: -0.0000

Data Index: 5154 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0658. Min Act: -0.0000

Data Index: 743383 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0652. Min Act: -0.0000

Data Index: 13095 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0617. Min Act: -0.0000

Data Index: 463726 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0655. Min Act: -0.0000

Data Index: 435562 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0614. Min Act: -0.0000

Data Index: 834160 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0550. Min Act: -0.0000

Data Index: 395400 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0592. Min Act: -0.0000

Data Index: 93289 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1222426 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0563. Min Act: -0.0000

Data Index: 226428 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0537. Min Act: -0.0000

Data Index: 24179 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0520. Min Act: -0.0000

Data Index: 985859 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1341336 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0532. Min Act: -0.0000

Data Index: 1092833 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0528. Min Act: -0.0000

Data Index: 303307 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0528. Min Act: -0.0000

Data Index: 382662 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0553. Min Act: -0.0000

Data Index: 735819 (C4 (Web Text))

Max Activating Token Index: 830