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

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

Neuron 2528 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1367286 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1486585 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1421850 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1432191 (Python Code)

Max Activating Token Index: 964

Text #4

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1415214 (Python Code)

Max Activating Token Index: 875

Text #5

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1535654 (Python Code)

Max Activating Token Index: 460

Text #6

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1705. Min Act: -0.0001

Data Index: 1428089 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1653642 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1639. Min Act: -0.0001

Data Index: 1371040 (Python Code)

Max Activating Token Index: 952

Text #9

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1642872 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1588089 (Python Code)

Max Activating Token Index: 921

Text #11

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1394901 (Python Code)

Max Activating Token Index: 850

Text #12

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1424734 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1535624 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1393288 (Python Code)

Max Activating Token Index: 305

Text #15

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1374433 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1635477 (Python Code)

Max Activating Token Index: 475

Text #17

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1466633 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1451349 (Python Code)

Max Activating Token Index: 312

Text #19

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1505552 (Python Code)

Max Activating Token Index: 545