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

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

Neuron 1351 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0869. Min Range: -1.0869

Max Act: 1.0869. Min Act: -0.0000

Data Index: 649900 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.0869. Min Range: -1.0869

Max Act: 1.0363. Min Act: -0.0000

Data Index: 783386 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1012397 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.9451. Min Act: -0.0000

Data Index: 768927 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7863. Min Act: -0.0000

Data Index: 321840 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1008028 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7370. Min Act: -0.0000

Data Index: 997581 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1196692 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7070. Min Act: -0.0000

Data Index: 604175 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1020938 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1157862 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1417460 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.6839. Min Act: -0.0000

Data Index: 525829 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1064088 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.5993. Min Act: -0.0000

Data Index: 387330 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.6491. Min Act: -0.0000

Data Index: 331793 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.7100. Min Act: -0.0000

Data Index: 94572 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.6392. Min Act: -0.0000

Data Index: 913672 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.6005. Min Act: -0.0000

Data Index: 171144 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.0869. Min Range: -1.0869

Max Act: 0.6201. Min Act: -0.0000

Data Index: 418614 (C4 (Web Text))

Max Activating Token Index: 894