Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1792 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.6625. Min Act: -0.0001

Data Index: 1423542 (Python Code)

Max Activating Token Index: 174

Text #1

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.6587. Min Act: -0.0001

Data Index: 1086379 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5890. Min Act: -0.0001

Data Index: 1359224 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5930. Min Act: -0.0001

Data Index: 1396829 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1150473 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.6091. Min Act: -0.0001

Data Index: 735780 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5732. Min Act: -0.0001

Data Index: 847809 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5813. Min Act: -0.0001

Data Index: 1205146 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5784. Min Act: -0.0001

Data Index: 946563 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5506. Min Act: -0.0001

Data Index: 1096083 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5598. Min Act: -0.0001

Data Index: 60639 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5413. Min Act: -0.0001

Data Index: 1184414 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5712. Min Act: -0.0001

Data Index: 284507 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5836. Min Act: -0.0001

Data Index: 363418 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5618. Min Act: -0.0001

Data Index: 1182941 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5749. Min Act: -0.0001

Data Index: 812065 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5506. Min Act: -0.0001

Data Index: 1059942 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5745. Min Act: -0.0001

Data Index: 52883 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5868. Min Act: -0.0001

Data Index: 166785 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.6625. Min Range: -0.6625

Max Act: 0.5702. Min Act: -0.0001

Data Index: 843475 (C4 (Web Text))

Max Activating Token Index: 443