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

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

Neuron 785 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.8556. Min Act: -0.0002

Data Index: 796813 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1190397 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7511. Min Act: -0.0002

Data Index: 387541 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7690. Min Act: -0.0002

Data Index: 1287371 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7792. Min Act: -0.0001

Data Index: 1207494 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7248. Min Act: -0.0002

Data Index: 1006782 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7545. Min Act: -0.0001

Data Index: 145560 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7483. Min Act: -0.0001

Data Index: 8681 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7200. Min Act: -0.0001

Data Index: 618545 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7201. Min Act: -0.0001

Data Index: 460065 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7373. Min Act: -0.0001

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.6726. Min Act: -0.0002

Data Index: 112978 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.6889. Min Act: -0.0002

Data Index: 1003741 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.6801. Min Act: -0.0002

Data Index: 1000434 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.6964. Min Act: -0.0001

Data Index: 1134324 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.6633. Min Act: -0.0002

Data Index: 723573 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.6908. Min Act: -0.0002

Data Index: 850110 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.7007. Min Act: -0.0001

Data Index: 255326 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.6742. Min Act: -0.0001

Data Index: 628590 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.8608. Min Range: -0.8608

Max Act: 0.6942. Min Act: -0.0001

Data Index: 488086 (C4 (Web Text))

Max Activating Token Index: 970