Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 775 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1685. Min Act: -0.0004

Data Index: 1529340 (Python Code)

Max Activating Token Index: 526

Text #1

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1675. Min Act: -0.0004

Data Index: 1564597 (Python Code)

Max Activating Token Index: 916

Text #2

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1624. Min Act: -0.0004

Data Index: 1483755 (Python Code)

Max Activating Token Index: 703

Text #3

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1618. Min Act: -0.0004

Data Index: 1470384 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1615. Min Act: -0.0004

Data Index: 1404099 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1582. Min Act: -0.0004

Data Index: 1583564 (Python Code)

Max Activating Token Index: 533

Text #6

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1556. Min Act: -0.0004

Data Index: 1647822 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1537. Min Act: -0.0004

Data Index: 1648201 (Python Code)

Max Activating Token Index: 789

Text #8

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1497. Min Act: -0.0004

Data Index: 1412576 (Python Code)

Max Activating Token Index: 618

Text #9

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1516. Min Act: -0.0004

Data Index: 1403482 (Python Code)

Max Activating Token Index: 798

Text #10

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1468. Min Act: -0.0004

Data Index: 1563679 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1465. Min Act: -0.0004

Data Index: 1477554 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1463. Min Act: -0.0004

Data Index: 1654269 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1463. Min Act: -0.0004

Data Index: 1502302 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1463. Min Act: -0.0004

Data Index: 1534826 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1462. Min Act: -0.0004

Data Index: 1626567 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1462. Min Act: -0.0004

Data Index: 1607840 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1459. Min Act: -0.0004

Data Index: 1391825 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1461. Min Act: -0.0004

Data Index: 1587358 (Python Code)

Max Activating Token Index: 799

Text #19

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1457. Min Act: -0.0004

Data Index: 1591756 (Python Code)

Max Activating Token Index: 5