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

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

Neuron 1862 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1591374 (Python Code)

Max Activating Token Index: 280

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1615301 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1552417 (Python Code)

Max Activating Token Index: 306

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1655659 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1473615 (Python Code)

Max Activating Token Index: 187

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1575314 (Python Code)

Max Activating Token Index: 363

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1468156 (Python Code)

Max Activating Token Index: 821

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1593980 (Python Code)

Max Activating Token Index: 390

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1524739 (Python Code)

Max Activating Token Index: 482

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1652662 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1602589 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1622216 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1393717 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1616074 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1398634 (Python Code)

Max Activating Token Index: 931

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1468997 (Python Code)

Max Activating Token Index: 406

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1513822 (Python Code)

Max Activating Token Index: 662

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1575621 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1564482 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1577359 (Python Code)

Max Activating Token Index: 85