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

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

Neuron 4089 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: 2.2621. Min Range: -2.2621

Max Act: 2.0094. Min Act: -0.0001

Data Index: 1518656 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 2.2621. Min Range: -2.2621

Max Act: 2.2558. Min Act: -0.0001

Data Index: 1563985 (Python Code)

Max Activating Token Index: 892

Text #2

Max Range: 2.2621. Min Range: -2.2621

Max Act: 2.1755. Min Act: -0.0000

Data Index: 1535425 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 2.2621. Min Range: -2.2621

Max Act: 2.2621. Min Act: -0.0000

Data Index: 1383708 (Python Code)

Max Activating Token Index: 143

Text #4

Max Range: 2.2621. Min Range: -2.2621

Max Act: 2.1625. Min Act: -0.0000

Data Index: 1453283 (Python Code)

Max Activating Token Index: 251

Text #5

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.9797. Min Act: -0.0001

Data Index: 1565799 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 2.2621. Min Range: -2.2621

Max Act: 2.0685. Min Act: -0.0000

Data Index: 1571743 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.9533. Min Act: -0.0000

Data Index: 1635801 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.9314. Min Act: -0.0000

Data Index: 1606083 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.9367. Min Act: -0.0000

Data Index: 1373050 (Python Code)

Max Activating Token Index: 429

Text #10

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.8975. Min Act: -0.0001

Data Index: 1538613 (Python Code)

Max Activating Token Index: 791

Text #11

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.9648. Min Act: -0.0000

Data Index: 1559685 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.8435. Min Act: -0.0000

Data Index: 1601448 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.9208. Min Act: -0.0000

Data Index: 1454162 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.9099. Min Act: -0.0000

Data Index: 1584858 (Python Code)

Max Activating Token Index: 736

Text #15

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.9276. Min Act: -0.0001

Data Index: 1438435 (Python Code)

Max Activating Token Index: 635

Text #16

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.7151. Min Act: -0.0000

Data Index: 1440364 (Python Code)

Max Activating Token Index: 817

Text #17

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.9684. Min Act: -0.0000

Data Index: 1629586 (Python Code)

Max Activating Token Index: 772

Text #18

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.7773. Min Act: -0.0001

Data Index: 1586503 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.2621. Min Range: -2.2621

Max Act: 1.7220. Min Act: -0.0000

Data Index: 1576067 (Python Code)

Max Activating Token Index: 622