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

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

Neuron 1598 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: 0.5556. Min Range: -0.5556

Max Act: 0.5556. Min Act: -0.0001

Data Index: 820686 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.5246. Min Act: -0.0000

Data Index: 43309 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.4101. Min Act: -0.0000

Data Index: 915513 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3629. Min Act: -0.0000

Data Index: 973772 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3651. Min Act: -0.0001

Data Index: 748724 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3500. Min Act: -0.0001

Data Index: 1185409 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1188818 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1016928 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3355. Min Act: -0.0000

Data Index: 918609 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1348884 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3197. Min Act: -0.0001

Data Index: 86449 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3388. Min Act: -0.0000

Data Index: 628749 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3262. Min Act: -0.0000

Data Index: 759078 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3030. Min Act: -0.0000

Data Index: 530874 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3215. Min Act: -0.0000

Data Index: 749145 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3062. Min Act: -0.0000

Data Index: 652541 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3135. Min Act: -0.0000

Data Index: 99013 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.3010. Min Act: -0.0000

Data Index: 553946 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.2996. Min Act: -0.0000

Data Index: 743780 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.5556. Min Range: -0.5556

Max Act: 0.2994. Min Act: -0.0000

Data Index: 302194 (C4 (Web Text))

Max Activating Token Index: 879