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

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

Neuron 5551 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2473. Min Act: -0.0000

Data Index: 615102 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2109. Min Act: 0.0000

Data Index: 110696 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2219. Min Act: -0.0000

Data Index: 642191 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2099. Min Act: -0.0000

Data Index: 240690 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2089. Min Act: 0.0000

Data Index: 1118875 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2006. Min Act: -0.0000

Data Index: 30406 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2058. Min Act: 0.0000

Data Index: 379646 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1955. Min Act: -0.0000

Data Index: 666517 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2009. Min Act: -0.0000

Data Index: 997218 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1894. Min Act: -0.0000

Data Index: 857400 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1088425 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1948. Min Act: 0.0000

Data Index: 1280542 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1792. Min Act: -0.0000

Data Index: 307513 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1849. Min Act: -0.0000

Data Index: 996743 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1131543 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1890. Min Act: -0.0000

Data Index: 417278 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1903. Min Act: -0.0000

Data Index: 255344 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1826. Min Act: -0.0000

Data Index: 860619 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1828. Min Act: -0.0000

Data Index: 236942 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1293146 (C4 (Web Text))

Max Activating Token Index: 976