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

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

Neuron 4808 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1273. Min Act: -0.0000

Data Index: 872358 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1161292 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0780. Min Act: -0.0000

Data Index: 623845 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1500232 (Python Code)

Max Activating Token Index: 416

Text #4

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0802. Min Act: -0.0000

Data Index: 647093 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0786. Min Act: -0.0000

Data Index: 135380 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0782. Min Act: -0.0000

Data Index: 241758 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1620196 (Python Code)

Max Activating Token Index: 901

Text #8

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0720. Min Act: -0.0000

Data Index: 979324 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1433154 (Python Code)

Max Activating Token Index: 651

Text #10

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0758. Min Act: -0.0000

Data Index: 394631 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0627. Min Act: -0.0000

Data Index: 438724 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1121667 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0683. Min Act: -0.0000

Data Index: 468364 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0699. Min Act: -0.0000

Data Index: 837654 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1618594 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0649. Min Act: -0.0000

Data Index: 373886 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1144685 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1538274 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1499440 (Python Code)

Max Activating Token Index: 627