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

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

Neuron 4466 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1722. Min Range: -3.1722

Max Act: 3.1722. Min Act: -0.0000

Data Index: 751543 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.2739. Min Act: -0.0000

Data Index: 1378085 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.3603. Min Act: -0.0000

Data Index: 1365636 (Python Code)

Max Activating Token Index: 590

Text #3

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.2011. Min Act: -0.0000

Data Index: 66689 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.9960. Min Act: -0.0000

Data Index: 1406854 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.1823. Min Act: -0.0000

Data Index: 900654 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1525942 (Python Code)

Max Activating Token Index: 469

Text #7

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.0511. Min Act: -0.0000

Data Index: 738134 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.0189. Min Act: -0.0000

Data Index: 1193040 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.9639. Min Act: -0.0000

Data Index: 91986 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.9493. Min Act: -0.0000

Data Index: 1575786 (Python Code)

Max Activating Token Index: 743

Text #11

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.9478. Min Act: -0.0000

Data Index: 1415499 (Python Code)

Max Activating Token Index: 680

Text #12

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.0504. Min Act: -0.0000

Data Index: 1529847 (Python Code)

Max Activating Token Index: 618

Text #13

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.9287. Min Act: -0.0000

Data Index: 1443384 (Python Code)

Max Activating Token Index: 285

Text #14

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.0290. Min Act: -0.0000

Data Index: 1390690 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.8964. Min Act: -0.0000

Data Index: 1471455 (Python Code)

Max Activating Token Index: 615

Text #16

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.9000. Min Act: -0.0000

Data Index: 1412158 (Python Code)

Max Activating Token Index: 747

Text #17

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.9705. Min Act: -0.0000

Data Index: 1550538 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.6672. Min Act: -0.0000

Data Index: 710959 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 3.1722. Min Range: -3.1722

Max Act: 1.8627. Min Act: -0.0000

Data Index: 1399114 (Python Code)

Max Activating Token Index: 698