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

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

Neuron 533 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1758. Min Act: -0.0002

Data Index: 1602437 (Python Code)

Max Activating Token Index: 827

Text #1

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1734. Min Act: -0.0002

Data Index: 1438736 (Python Code)

Max Activating Token Index: 689

Text #2

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1665. Min Act: -0.0002

Data Index: 1479464 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1679. Min Act: -0.0002

Data Index: 1606244 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1649. Min Act: -0.0002

Data Index: 1631183 (Python Code)

Max Activating Token Index: 294

Text #5

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1665. Min Act: -0.0002

Data Index: 1536822 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1609. Min Act: -0.0002

Data Index: 1450097 (Python Code)

Max Activating Token Index: 716

Text #7

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1619. Min Act: -0.0002

Data Index: 1450611 (Python Code)

Max Activating Token Index: 740

Text #8

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1593. Min Act: -0.0002

Data Index: 1554248 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1560. Min Act: -0.0002

Data Index: 1502347 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1558. Min Act: -0.0002

Data Index: 1407677 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1560. Min Act: -0.0002

Data Index: 1506690 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1561. Min Act: -0.0002

Data Index: 1535985 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1525. Min Act: -0.0002

Data Index: 1568107 (Python Code)

Max Activating Token Index: 601

Text #14

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1533. Min Act: -0.0002

Data Index: 1504062 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1545. Min Act: -0.0002

Data Index: 1466637 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1547. Min Act: -0.0002

Data Index: 1618547 (Python Code)

Max Activating Token Index: 965

Text #17

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1546. Min Act: -0.0002

Data Index: 1560925 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1517. Min Act: -0.0002

Data Index: 1577079 (Python Code)

Max Activating Token Index: 729

Text #19

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1537. Min Act: -0.0002

Data Index: 1523040 (Python Code)

Max Activating Token Index: 886