Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3880 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.2080. Min Act: -0.0000

Data Index: 968017 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1802. Min Act: -0.0001

Data Index: 803927 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1865. Min Act: -0.0000

Data Index: 898780 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1096269 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1057126 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1618. Min Act: -0.0000

Data Index: 559833 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1811. Min Act: -0.0001

Data Index: 911301 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1615. Min Act: -0.0001

Data Index: 102345 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1769. Min Act: -0.0000

Data Index: 840553 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1655. Min Act: -0.0000

Data Index: 363232 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1535. Min Act: -0.0000

Data Index: 658899 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1621. Min Act: -0.0001

Data Index: 365216 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1561. Min Act: -0.0000

Data Index: 374631 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1563. Min Act: -0.0001

Data Index: 596250 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1518. Min Act: -0.0001

Data Index: 1130500 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1501. Min Act: -0.0000

Data Index: 637632 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1503. Min Act: -0.0000

Data Index: 466665 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1530. Min Act: -0.0001

Data Index: 433935 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1467. Min Act: -0.0001

Data Index: 377611 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.2080. Min Range: -0.2080

Max Act: 0.1472. Min Act: -0.0000

Data Index: 833318 (C4 (Web Text))

Max Activating Token Index: 451