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

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

Neuron 3393 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1171169 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1381191 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1256511 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0697. Min Act: -0.0001

Data Index: 266810 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0720. Min Act: -0.0001

Data Index: 948953 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0695. Min Act: -0.0001

Data Index: 235503 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0692. Min Act: -0.0002

Data Index: 591047 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0683. Min Act: -0.0001

Data Index: 253677 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0686. Min Act: -0.0001

Data Index: 207398 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0684. Min Act: -0.0001

Data Index: 103916 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0681. Min Act: -0.0001

Data Index: 790442 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1006497 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0687. Min Act: -0.0001

Data Index: 566412 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1235590 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0684. Min Act: -0.0001

Data Index: 976059 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0683. Min Act: -0.0001

Data Index: 391835 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0689. Min Act: -0.0001

Data Index: 982502 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0678. Min Act: -0.0001

Data Index: 66984 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1110025 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1152654 (C4 (Web Text))

Max Activating Token Index: 266