Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1769 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 1.0445. Min Range: -1.0445

Max Act: 1.0445. Min Act: -0.0005

Data Index: 892654 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.9036. Min Act: -0.0005

Data Index: 608820 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8718. Min Act: -0.0005

Data Index: 621532 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8433. Min Act: -0.0005

Data Index: 395701 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7741. Min Act: -0.0005

Data Index: 753144 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.9192. Min Act: -0.0005

Data Index: 808460 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8053. Min Act: -0.0005

Data Index: 634943 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7828. Min Act: -0.0005

Data Index: 1039653 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8314. Min Act: -0.0005

Data Index: 1342325 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8001. Min Act: -0.0005

Data Index: 494079 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8267. Min Act: -0.0005

Data Index: 415612 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7819. Min Act: -0.0005

Data Index: 206842 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7089. Min Act: -0.0005

Data Index: 1036727 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.6926. Min Act: -0.0005

Data Index: 451780 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7379. Min Act: -0.0005

Data Index: 969295 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7775. Min Act: -0.0005

Data Index: 1203207 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7075. Min Act: -0.0005

Data Index: 281896 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.6798. Min Act: -0.0005

Data Index: 236325 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7056. Min Act: -0.0005

Data Index: 887964 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7057. Min Act: -0.0005

Data Index: 1323351 (C4 (Web Text))

Max Activating Token Index: 375