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

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

Neuron 4292 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2926. Min Act: -0.0002

Data Index: 1365965 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3040. Min Act: -0.0002

Data Index: 1380233 (Python Code)

Max Activating Token Index: 470

Text #2

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3015. Min Act: -0.0002

Data Index: 1443577 (Python Code)

Max Activating Token Index: 951

Text #3

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1469768 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1582165 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1638209 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1621944 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1471714 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1569186 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1408153 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1487822 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2843. Min Act: -0.0002

Data Index: 1400764 (Python Code)

Max Activating Token Index: 351

Text #12

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2408. Min Act: -0.0002

Data Index: 1520915 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2679. Min Act: -0.0002

Data Index: 1592114 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2679. Min Act: -0.0002

Data Index: 1363817 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2898. Min Act: -0.0002

Data Index: 1608621 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2786. Min Act: -0.0002

Data Index: 1379730 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2786. Min Act: -0.0002

Data Index: 1435771 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2786. Min Act: -0.0002

Data Index: 1467349 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.3115. Min Range: -0.3115

Max Act: 0.2786. Min Act: -0.0002

Data Index: 1406420 (Python Code)

Max Activating Token Index: 10