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

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

Neuron 3592 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1632739 (Python Code)

Max Activating Token Index: 958

Text #1

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1599079 (Python Code)

Max Activating Token Index: 556

Text #2

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1570847 (Python Code)

Max Activating Token Index: 822

Text #3

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1655569 (Python Code)

Max Activating Token Index: 569

Text #4

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1433325 (Python Code)

Max Activating Token Index: 244

Text #5

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1394405 (Python Code)

Max Activating Token Index: 818

Text #6

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1614513 (Python Code)

Max Activating Token Index: 548

Text #7

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1571853 (Python Code)

Max Activating Token Index: 935

Text #8

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1546913 (Python Code)

Max Activating Token Index: 833

Text #9

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1429898 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1613744 (Python Code)

Max Activating Token Index: 766

Text #11

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1629828 (Python Code)

Max Activating Token Index: 994

Text #12

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1508845 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1627899 (Python Code)

Max Activating Token Index: 456

Text #14

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1505167 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1379692 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1498040 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1465445 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1370068 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1542725 (Python Code)

Max Activating Token Index: 1022