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

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

Neuron 4332 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1983. Min Act: -0.0001

Data Index: 116856 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1877. Min Act: -0.0000

Data Index: 863351 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1228703 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1322736 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1737. Min Act: -0.0000

Data Index: 376395 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1787. Min Act: -0.0000

Data Index: 661869 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1754. Min Act: -0.0001

Data Index: 529398 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1602. Min Act: -0.0001

Data Index: 871382 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1096554 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1541. Min Act: -0.0001

Data Index: 784874 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1608. Min Act: -0.0000

Data Index: 606087 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1309539 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1592. Min Act: -0.0000

Data Index: 979533 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1563. Min Act: -0.0000

Data Index: 636661 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1549. Min Act: -0.0000

Data Index: 779079 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1487. Min Act: -0.0001

Data Index: 264739 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1520. Min Act: -0.0000

Data Index: 795291 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1177396 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1006005 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1449. Min Act: -0.0000

Data Index: 637225 (C4 (Web Text))

Max Activating Token Index: 1019