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

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

Neuron 1142 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1183676 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0754. Min Act: -0.0002

Data Index: 566824 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0779. Min Act: -0.0002

Data Index: 957423 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0762. Min Act: -0.0002

Data Index: 238393 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0710. Min Act: -0.0002

Data Index: 833218 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0672. Min Act: -0.0002

Data Index: 141855 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0684. Min Act: -0.0002

Data Index: 139351 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0680. Min Act: -0.0002

Data Index: 321715 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1078066 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0691. Min Act: -0.0002

Data Index: 458764 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0665. Min Act: -0.0002

Data Index: 939225 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0682. Min Act: -0.0002

Data Index: 581566 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1248845 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0656. Min Act: -0.0002

Data Index: 55895 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0618. Min Act: -0.0002

Data Index: 56508 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0638. Min Act: -0.0002

Data Index: 610301 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0634. Min Act: -0.0002

Data Index: 380451 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0633. Min Act: -0.0002

Data Index: 96483 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0642. Min Act: -0.0002

Data Index: 44929 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1010443 (C4 (Web Text))

Max Activating Token Index: 113