Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3352 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1005603 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1372516 (Python Code)

Max Activating Token Index: 75

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0834. Min Act: -0.0002

Data Index: 354817 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1254947 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1590881 (Python Code)

Max Activating Token Index: 159

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0758. Min Act: -0.0002

Data Index: 473641 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0787. Min Act: -0.0002

Data Index: 485922 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0742. Min Act: -0.0002

Data Index: 191643 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0750. Min Act: -0.0002

Data Index: 454293 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0754. Min Act: -0.0002

Data Index: 55831 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0762. Min Act: -0.0002

Data Index: 998183 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1628644 (Python Code)

Max Activating Token Index: 711

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1029869 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0725. Min Act: -0.0002

Data Index: 809429 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0672. Min Act: -0.0002

Data Index: 194912 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0803. Min Act: -0.0002

Data Index: 144689 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1012505 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1492781 (Python Code)

Max Activating Token Index: 677

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1525536 (Python Code)

Max Activating Token Index: 606

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0661. Min Act: -0.0002

Data Index: 884961 (C4 (Web Text))

Max Activating Token Index: 82