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

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

Neuron 3526 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: 0.6976. Min Range: -0.6976

Max Act: 0.6848. Min Act: -0.0002

Data Index: 1381368 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6975. Min Act: -0.0002

Data Index: 1498636 (Python Code)

Max Activating Token Index: 240

Text #2

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6976. Min Act: -0.0002

Data Index: 1440522 (Python Code)

Max Activating Token Index: 515

Text #3

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6077. Min Act: -0.0002

Data Index: 1485172 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5753. Min Act: -0.0002

Data Index: 1493631 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6508. Min Act: -0.0002

Data Index: 1391179 (Python Code)

Max Activating Token Index: 308

Text #6

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6640. Min Act: -0.0002

Data Index: 1641343 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6026. Min Act: -0.0002

Data Index: 1474233 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6419. Min Act: -0.0002

Data Index: 1505369 (Python Code)

Max Activating Token Index: 830

Text #9

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5845. Min Act: -0.0002

Data Index: 1377396 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6025. Min Act: -0.0002

Data Index: 1461109 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5894. Min Act: -0.0002

Data Index: 1566030 (Python Code)

Max Activating Token Index: 989

Text #12

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6614. Min Act: -0.0002

Data Index: 1458717 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5816. Min Act: -0.0002

Data Index: 1641946 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.6128. Min Act: -0.0002

Data Index: 1509005 (Python Code)

Max Activating Token Index: 208

Text #15

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5309. Min Act: -0.0002

Data Index: 1546965 (Python Code)

Max Activating Token Index: 811

Text #16

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5709. Min Act: -0.0002

Data Index: 1507206 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5667. Min Act: -0.0002

Data Index: 1640205 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5525. Min Act: -0.0002

Data Index: 1655472 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 0.6976. Min Range: -0.6976

Max Act: 0.5964. Min Act: -0.0002

Data Index: 1388893 (Python Code)

Max Activating Token Index: 32