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

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

Neuron 3622 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: 0.1051. Min Range: -0.1051

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1645996 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1432960 (Python Code)

Max Activating Token Index: 438

Text #2

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1465365 (Python Code)

Max Activating Token Index: 291

Text #3

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1627256 (Python Code)

Max Activating Token Index: 289

Text #4

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1553962 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1551077 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1536836 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1655797 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1510951 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1652713 (Python Code)

Max Activating Token Index: 65

Text #10

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1594855 (Python Code)

Max Activating Token Index: 102

Text #11

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1467860 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1409320 (Python Code)

Max Activating Token Index: 714

Text #13

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1565434 (Python Code)

Max Activating Token Index: 239

Text #14

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1505214 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1612606 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1378068 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1396405 (Python Code)

Max Activating Token Index: 523

Text #18

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1592522 (Python Code)

Max Activating Token Index: 970

Text #19

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1365326 (Python Code)

Max Activating Token Index: 154