Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2470 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1620028 (Python Code)

Max Activating Token Index: 680

Text #1

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1519369 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1364660 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1550644 (Python Code)

Max Activating Token Index: 971

Text #4

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1564837 (Python Code)

Max Activating Token Index: 539

Text #5

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1463023 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1438913 (Python Code)

Max Activating Token Index: 225

Text #7

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1618296 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1595623 (Python Code)

Max Activating Token Index: 626

Text #9

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1566615 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1577808 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1423510 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1427697 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1443. Min Act: -0.0001

Data Index: 1383008 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1564513 (Python Code)

Max Activating Token Index: 496

Text #15

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1369344 (Python Code)

Max Activating Token Index: 880

Text #16

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1604451 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1417083 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1650771 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1554079 (Python Code)

Max Activating Token Index: 349