Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3428 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1082596 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2208. Min Act: -0.0000

Data Index: 639963 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1343101 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.2003. Min Act: -0.0001

Data Index: 445733 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1968. Min Act: -0.0000

Data Index: 132904 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1987. Min Act: -0.0000

Data Index: 14729 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1896. Min Act: -0.0001

Data Index: 1333306 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1087695 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1754. Min Act: -0.0001

Data Index: 523829 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1804. Min Act: -0.0001

Data Index: 383275 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1848. Min Act: -0.0001

Data Index: 843924 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1696. Min Act: -0.0001

Data Index: 600708 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1309020 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1605. Min Act: -0.0000

Data Index: 431349 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1149205 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1147916 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1556. Min Act: -0.0000

Data Index: 235223 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1575. Min Act: -0.0001

Data Index: 571724 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1016459 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.2729. Min Range: -0.2729

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1046662 (C4 (Web Text))

Max Activating Token Index: 388