Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1563 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.2724. Min Act: -0.0000

Data Index: 190769 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1310893 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9887. Min Act: -0.0000

Data Index: 917182 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9888. Min Act: -0.0000

Data Index: 328359 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9557. Min Act: -0.0000

Data Index: 34412 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8655. Min Act: -0.0000

Data Index: 735926 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8851. Min Act: -0.0000

Data Index: 80867 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8675. Min Act: -0.0000

Data Index: 367352 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8859. Min Act: -0.0000

Data Index: 225454 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8972. Min Act: -0.0000

Data Index: 849871 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1021270 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8407. Min Act: -0.0000

Data Index: 113470 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7472. Min Act: -0.0000

Data Index: 156622 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8559. Min Act: -0.0000

Data Index: 591108 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8330. Min Act: -0.0000

Data Index: 946780 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1266149 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1039300 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8025. Min Act: -0.0000

Data Index: 745071 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.8121. Min Act: -0.0000

Data Index: 2350 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.7368. Min Act: -0.0000

Data Index: 790613 (C4 (Web Text))

Max Activating Token Index: 762