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

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

Neuron 3660 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.6044. Min Act: -0.0000

Data Index: 692999 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5829. Min Act: -0.0000

Data Index: 448635 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5329. Min Act: -0.0000

Data Index: 137804 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4321. Min Act: -0.0000

Data Index: 185345 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4187. Min Act: -0.0000

Data Index: 564795 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4138. Min Act: -0.0000

Data Index: 239794 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4088. Min Act: -0.0000

Data Index: 69904 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4135. Min Act: -0.0000

Data Index: 508051 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4047. Min Act: -0.0000

Data Index: 828997 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3974. Min Act: -0.0000

Data Index: 250591 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3821. Min Act: -0.0000

Data Index: 624597 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1041504 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4065. Min Act: -0.0000

Data Index: 273006 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3674. Min Act: -0.0000

Data Index: 827973 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3781. Min Act: -0.0000

Data Index: 575384 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3754. Min Act: -0.0000

Data Index: 220207 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3597. Min Act: -0.0000

Data Index: 302554 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3843. Min Act: -0.0000

Data Index: 995301 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3579. Min Act: -0.0000

Data Index: 360955 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3565. Min Act: -0.0000

Data Index: 508469 (C4 (Web Text))

Max Activating Token Index: 845