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

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

Neuron 4725 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4882. Min Range: -3.4882

Max Act: 3.4882. Min Act: -0.0000

Data Index: 1523779 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.6722. Min Act: -0.0000

Data Index: 1581297 (Python Code)

Max Activating Token Index: 945

Text #2

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.7243. Min Act: -0.0000

Data Index: 1463175 (Python Code)

Max Activating Token Index: 290

Text #3

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.7782. Min Act: -0.0000

Data Index: 1404954 (Python Code)

Max Activating Token Index: 454

Text #4

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.5497. Min Act: -0.0000

Data Index: 1455297 (Python Code)

Max Activating Token Index: 811

Text #5

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.2631. Min Act: -0.0000

Data Index: 1628046 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.4899. Min Act: 0.0001

Data Index: 1535527 (Python Code)

Max Activating Token Index: 448

Text #7

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.1298. Min Act: -0.0000

Data Index: 1570937 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.0772. Min Act: -0.0000

Data Index: 1362545 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.0635. Min Act: -0.0000

Data Index: 1401411 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 3.4882. Min Range: -3.4882

Max Act: 1.8281. Min Act: -0.0000

Data Index: 1475734 (Python Code)

Max Activating Token Index: 597

Text #11

Max Range: 3.4882. Min Range: -3.4882

Max Act: 2.1031. Min Act: -0.0000

Data Index: 1584218 (Python Code)

Max Activating Token Index: 317

Text #12

Max Range: 3.4882. Min Range: -3.4882

Max Act: 1.8718. Min Act: -0.0000

Data Index: 1420404 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 3.4882. Min Range: -3.4882

Max Act: 1.9551. Min Act: -0.0000

Data Index: 1392538 (Python Code)

Max Activating Token Index: 557

Text #14

Max Range: 3.4882. Min Range: -3.4882

Max Act: 1.8231. Min Act: 0.0000

Data Index: 1608336 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 3.4882. Min Range: -3.4882

Max Act: 1.8124. Min Act: -0.0000

Data Index: 1569791 (Python Code)

Max Activating Token Index: 454

Text #16

Max Range: 3.4882. Min Range: -3.4882

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1488859 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 3.4882. Min Range: -3.4882

Max Act: 1.8751. Min Act: -0.0000

Data Index: 1646193 (Python Code)

Max Activating Token Index: 446

Text #18

Max Range: 3.4882. Min Range: -3.4882

Max Act: 1.8659. Min Act: -0.0000

Data Index: 1423914 (Python Code)

Max Activating Token Index: 460

Text #19

Max Range: 3.4882. Min Range: -3.4882

Max Act: 1.7815. Min Act: -0.0000

Data Index: 1609153 (Python Code)

Max Activating Token Index: 899