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

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

Neuron 3206 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0766. Min Act: -0.0001

Data Index: 282396 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1106283 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0741. Min Act: -0.0001

Data Index: 824815 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0806. Min Act: -0.0001

Data Index: 186686 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1157408 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1153249 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0717. Min Act: -0.0001

Data Index: 346019 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0633. Min Act: -0.0001

Data Index: 80411 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1168301 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1008060 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0645. Min Act: -0.0001

Data Index: 594516 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0656. Min Act: -0.0001

Data Index: 273020 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0749. Min Act: -0.0001

Data Index: 476803 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1217263 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0615. Min Act: -0.0001

Data Index: 685290 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0744. Min Act: -0.0001

Data Index: 968177 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1119708 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1103571 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0592. Min Act: -0.0001

Data Index: 357023 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1151105 (C4 (Web Text))

Max Activating Token Index: 69