Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3445 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.8357. Min Act: -0.0001

Data Index: 1425672 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.8380. Min Act: -0.0001

Data Index: 1379105 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.8380. Min Act: -0.0001

Data Index: 1369977 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.8067. Min Act: -0.0001

Data Index: 1523427 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7863. Min Act: -0.0001

Data Index: 1469551 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7875. Min Act: -0.0001

Data Index: 1635287 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.8290. Min Act: -0.0001

Data Index: 1527033 (Python Code)

Max Activating Token Index: 844

Text #7

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.8258. Min Act: -0.0001

Data Index: 1369833 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7866. Min Act: -0.0001

Data Index: 1609630 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7342. Min Act: -0.0001

Data Index: 1554144 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.8188. Min Act: -0.0001

Data Index: 1572900 (Python Code)

Max Activating Token Index: 872

Text #11

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.8652. Min Act: -0.0001

Data Index: 1482953 (Python Code)

Max Activating Token Index: 948

Text #12

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.6798. Min Act: -0.0001

Data Index: 1636260 (Python Code)

Max Activating Token Index: 912

Text #13

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7999. Min Act: -0.0001

Data Index: 1510234 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7653. Min Act: -0.0001

Data Index: 1575309 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7630. Min Act: -0.0001

Data Index: 1584405 (Python Code)

Max Activating Token Index: 390

Text #16

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7137. Min Act: -0.0001

Data Index: 1365196 (Python Code)

Max Activating Token Index: 967

Text #17

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7350. Min Act: -0.0001

Data Index: 1415853 (Python Code)

Max Activating Token Index: 869

Text #18

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.7607. Min Act: -0.0001

Data Index: 1551683 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 0.8652. Min Range: -0.8652

Max Act: 0.6879. Min Act: -0.0001

Data Index: 1640249 (Python Code)

Max Activating Token Index: 357