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

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

Neuron 3817 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7744. Min Act: -0.0001

Data Index: 638044 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1211339 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6548. Min Act: -0.0001

Data Index: 459124 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6720. Min Act: -0.0001

Data Index: 564434 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6258. Min Act: -0.0001

Data Index: 548434 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6244. Min Act: -0.0001

Data Index: 1177992 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5878. Min Act: -0.0001

Data Index: 984166 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6071. Min Act: -0.0001

Data Index: 993224 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5969. Min Act: -0.0001

Data Index: 939258 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5554. Min Act: -0.0001

Data Index: 816379 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5949. Min Act: -0.0001

Data Index: 638463 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5678. Min Act: -0.0001

Data Index: 819857 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5686. Min Act: -0.0001

Data Index: 370225 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5922. Min Act: -0.0001

Data Index: 1169606 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5805. Min Act: -0.0001

Data Index: 1098114 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5871. Min Act: -0.0001

Data Index: 789329 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5478. Min Act: -0.0001

Data Index: 442425 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5463. Min Act: -0.0001

Data Index: 1110484 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5592. Min Act: -0.0001

Data Index: 539632 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5570. Min Act: -0.0001

Data Index: 728624 (C4 (Web Text))

Max Activating Token Index: 24