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

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

Neuron 2153 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1753. Min Act: -0.0001

Data Index: 520322 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1762. Min Act: -0.0001

Data Index: 97898 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1456. Min Act: -0.0001

Data Index: 421367 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1666. Min Act: -0.0001

Data Index: 11290 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1681. Min Act: -0.0001

Data Index: 704129 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1056925 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1091467 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1426. Min Act: -0.0001

Data Index: 708229 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1598. Min Act: -0.0001

Data Index: 789929 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1592. Min Act: -0.0001

Data Index: 153163 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1328890 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1492. Min Act: -0.0001

Data Index: 975019 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1504. Min Act: -0.0001

Data Index: 727307 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1513. Min Act: -0.0001

Data Index: 650764 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1586. Min Act: -0.0001

Data Index: 363670 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1551. Min Act: -0.0001

Data Index: 73768 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1351108 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1228825 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1168888 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1503. Min Act: -0.0001

Data Index: 60377 (C4 (Web Text))

Max Activating Token Index: 328