Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2437 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1443098 (Python Code)

Max Activating Token Index: 559

Text #1

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1383416 (Python Code)

Max Activating Token Index: 181

Text #2

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1457108 (Python Code)

Max Activating Token Index: 82

Text #3

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1440136 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1385540 (Python Code)

Max Activating Token Index: 444

Text #5

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1622823 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1701. Min Act: -0.0000

Data Index: 443319 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1628360 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1632170 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1455103 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1414130 (Python Code)

Max Activating Token Index: 966

Text #11

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1404740 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1375948 (Python Code)

Max Activating Token Index: 439

Text #13

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1583679 (Python Code)

Max Activating Token Index: 392

Text #14

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1421141 (Python Code)

Max Activating Token Index: 753

Text #15

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1600709 (Python Code)

Max Activating Token Index: 586

Text #16

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1574258 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1637097 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1545947 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1637220 (Python Code)

Max Activating Token Index: 181