Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1082 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0740. Min Act: -0.0005

Data Index: 1630241 (Python Code)

Max Activating Token Index: 915

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0005

Data Index: 1369712 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0750. Min Act: -0.0005

Data Index: 1489370 (Python Code)

Max Activating Token Index: 220

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0721. Min Act: -0.0005

Data Index: 1570499 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0718. Min Act: -0.0005

Data Index: 1530360 (Python Code)

Max Activating Token Index: 892

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0714. Min Act: -0.0005

Data Index: 1519213 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0697. Min Act: -0.0005

Data Index: 1608178 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0703. Min Act: -0.0005

Data Index: 1596122 (Python Code)

Max Activating Token Index: 402

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0701. Min Act: -0.0005

Data Index: 1569666 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0698. Min Act: -0.0005

Data Index: 1639012 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0679. Min Act: -0.0005

Data Index: 1494107 (Python Code)

Max Activating Token Index: 721

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0696. Min Act: -0.0006

Data Index: 1521154 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0689. Min Act: -0.0005

Data Index: 1443782 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0676. Min Act: -0.0005

Data Index: 1594398 (Python Code)

Max Activating Token Index: 653

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0676. Min Act: -0.0005

Data Index: 1633283 (Python Code)

Max Activating Token Index: 325

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0650. Min Act: -0.0005

Data Index: 1399978 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0670. Min Act: -0.0005

Data Index: 1363065 (Python Code)

Max Activating Token Index: 185

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0667. Min Act: -0.0005

Data Index: 1569348 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0696. Min Act: -0.0005

Data Index: 1620184 (Python Code)

Max Activating Token Index: 998

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0628. Min Act: -0.0005

Data Index: 1598771 (Python Code)

Max Activating Token Index: 1009