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

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

Neuron 3577 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: 1.0000. Min Range: -1.0000

Max Act: 0.9434. Min Act: -0.0001

Data Index: 330826 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.0000. Min Range: -1.0000

Max Act: 1.0000. Min Act: -0.0002

Data Index: 200738 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.9090. Min Act: -0.0002

Data Index: 789970 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.9024. Min Act: -0.0001

Data Index: 1120401 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8729. Min Act: -0.0001

Data Index: 758748 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8764. Min Act: -0.0002

Data Index: 1299841 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8652. Min Act: -0.0002

Data Index: 1355915 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8643. Min Act: -0.0002

Data Index: 441299 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8114. Min Act: -0.0002

Data Index: 667292 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8847. Min Act: -0.0001

Data Index: 861323 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8654. Min Act: -0.0002

Data Index: 230989 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8537. Min Act: -0.0001

Data Index: 387610 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8465. Min Act: -0.0001

Data Index: 412181 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8604. Min Act: -0.0001

Data Index: 115145 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8156. Min Act: -0.0001

Data Index: 544263 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8228. Min Act: -0.0001

Data Index: 900191 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8584. Min Act: -0.0002

Data Index: 410453 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8636. Min Act: -0.0001

Data Index: 1268704 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8640. Min Act: -0.0001

Data Index: 980342 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7976. Min Act: -0.0001

Data Index: 778684 (C4 (Web Text))

Max Activating Token Index: 780