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

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

Neuron 2215 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1542219 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1588215 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1162356 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1394342 (Python Code)

Max Activating Token Index: 230

Text #4

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1667. Min Act: -0.0001

Data Index: 328022 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1565907 (Python Code)

Max Activating Token Index: 454

Text #6

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1549. Min Act: -0.0001

Data Index: 427866 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1514911 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1764. Min Act: -0.0001

Data Index: 68748 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1677. Min Act: -0.0001

Data Index: 1637144 (Python Code)

Max Activating Token Index: 174

Text #10

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1466821 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1549. Min Act: -0.0001

Data Index: 891961 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1390929 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1376800 (Python Code)

Max Activating Token Index: 323

Text #14

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1710. Min Act: -0.0001

Data Index: 1405177 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1655. Min Act: -0.0001

Data Index: 1523132 (Python Code)

Max Activating Token Index: 957

Text #16

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1635273 (Python Code)

Max Activating Token Index: 351

Text #17

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1409196 (Python Code)

Max Activating Token Index: 399

Text #18

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1492493 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1547. Min Act: -0.0001

Data Index: 1550152 (Python Code)

Max Activating Token Index: 575