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

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

Neuron 2516 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: 0.0824. Min Range: -0.0824

Max Act: 0.0798. Min Act: -0.0000

Data Index: 806941 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0000

Data Index: 665722 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0816. Min Act: -0.0001

Data Index: 457368 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0714. Min Act: -0.0000

Data Index: 595568 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0687. Min Act: -0.0000

Data Index: 792046 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1022291 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0710. Min Act: -0.0000

Data Index: 392680 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0699. Min Act: -0.0001

Data Index: 589273 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0708. Min Act: -0.0000

Data Index: 541797 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1083203 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0658. Min Act: -0.0000

Data Index: 116691 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0674. Min Act: -0.0001

Data Index: 784302 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0654. Min Act: -0.0000

Data Index: 130422 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1232625 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1147188 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0618. Min Act: -0.0001

Data Index: 550920 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0595. Min Act: -0.0001

Data Index: 463323 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0642. Min Act: -0.0000

Data Index: 483268 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1236166 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0594. Min Act: -0.0000

Data Index: 261357 (C4 (Web Text))

Max Activating Token Index: 918