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

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

Neuron 2901 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1873. Min Range: -2.1873

Max Act: 2.1006. Min Act: -0.0000

Data Index: 1615321 (Python Code)

Max Activating Token Index: 520

Text #1

Max Range: 2.1873. Min Range: -2.1873

Max Act: 2.1873. Min Act: -0.0000

Data Index: 1373426 (Python Code)

Max Activating Token Index: 890

Text #2

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.8667. Min Act: -0.0000

Data Index: 1360892 (Python Code)

Max Activating Token Index: 967

Text #3

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.7731. Min Act: -0.0000

Data Index: 1595166 (Python Code)

Max Activating Token Index: 852

Text #4

Max Range: 2.1873. Min Range: -2.1873

Max Act: 2.0587. Min Act: -0.0000

Data Index: 1611155 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.7683. Min Act: -0.0000

Data Index: 1580035 (Python Code)

Max Activating Token Index: 127

Text #6

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.7800. Min Act: -0.0000

Data Index: 1449412 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.6051. Min Act: -0.0000

Data Index: 1536749 (Python Code)

Max Activating Token Index: 1019

Text #8

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.6974. Min Act: -0.0000

Data Index: 446203 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.4770. Min Act: -0.0000

Data Index: 1466705 (Python Code)

Max Activating Token Index: 615

Text #10

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1606262 (Python Code)

Max Activating Token Index: 250

Text #11

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.6866. Min Act: -0.0000

Data Index: 1653809 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.7037. Min Act: -0.0000

Data Index: 1570462 (Python Code)

Max Activating Token Index: 589

Text #13

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.5683. Min Act: -0.0000

Data Index: 1513092 (Python Code)

Max Activating Token Index: 34

Text #14

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.5953. Min Act: -0.0000

Data Index: 1564664 (Python Code)

Max Activating Token Index: 636

Text #15

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.5850. Min Act: -0.0000

Data Index: 1581410 (Python Code)

Max Activating Token Index: 120

Text #16

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1453266 (Python Code)

Max Activating Token Index: 585

Text #17

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.7029. Min Act: -0.0000

Data Index: 1550414 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.5549. Min Act: -0.0000

Data Index: 1460434 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 2.1873. Min Range: -2.1873

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1413556 (Python Code)

Max Activating Token Index: 778