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

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

Neuron 714 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1767. Min Act: -0.0000

Data Index: 794573 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1636965 (Python Code)

Max Activating Token Index: 743

Text #2

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1218159 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1752. Min Act: -0.0000

Data Index: 571070 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1678. Min Act: -0.0001

Data Index: 1637436 (Python Code)

Max Activating Token Index: 843

Text #5

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1383785 (Python Code)

Max Activating Token Index: 743

Text #6

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1648447 (Python Code)

Max Activating Token Index: 480

Text #7

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1304597 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1471849 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1621. Min Act: -0.0001

Data Index: 1476768 (Python Code)

Max Activating Token Index: 508

Text #10

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1647. Min Act: -0.0001

Data Index: 782793 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1462. Min Act: -0.0001

Data Index: 1524992 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1454863 (Python Code)

Max Activating Token Index: 995

Text #13

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1599892 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1505318 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1554180 (Python Code)

Max Activating Token Index: 743

Text #16

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1573458 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1600687 (Python Code)

Max Activating Token Index: 785

Text #18

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1520539 (Python Code)

Max Activating Token Index: 760

Text #19

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1492. Min Act: -0.0001

Data Index: 886072 (C4 (Web Text))

Max Activating Token Index: 688