Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 801 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1797. Min Act: -0.0001

Data Index: 1450991 (Python Code)

Max Activating Token Index: 644

Text #1

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1447817 (Python Code)

Max Activating Token Index: 222

Text #2

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1416655 (Python Code)

Max Activating Token Index: 557

Text #3

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1568578 (Python Code)

Max Activating Token Index: 499

Text #4

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1458341 (Python Code)

Max Activating Token Index: 510

Text #5

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1377197 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1387444 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1644. Min Act: -0.0001

Data Index: 1504866 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1478041 (Python Code)

Max Activating Token Index: 755

Text #9

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1651182 (Python Code)

Max Activating Token Index: 300

Text #10

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1716. Min Act: -0.0001

Data Index: 1464580 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1531. Min Act: -0.0001

Data Index: 1590001 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1506718 (Python Code)

Max Activating Token Index: 281

Text #13

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1537570 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1632126 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1611420 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1366835 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1491177 (Python Code)

Max Activating Token Index: 677

Text #18

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1457111 (Python Code)

Max Activating Token Index: 561

Text #19

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1550347 (Python Code)

Max Activating Token Index: 232