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

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

Neuron 521 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0006

Data Index: 859419 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0700. Min Act: -0.0006

Data Index: 1035147 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0652. Min Act: -0.0006

Data Index: 1029143 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0672. Min Act: -0.0006

Data Index: 115390 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0689. Min Act: -0.0006

Data Index: 59839 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0733. Min Act: -0.0006

Data Index: 1027021 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0630. Min Act: -0.0006

Data Index: 176246 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0594. Min Act: -0.0006

Data Index: 324411 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0623. Min Act: -0.0006

Data Index: 83752 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0635. Min Act: -0.0006

Data Index: 227776 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0572. Min Act: -0.0006

Data Index: 1194831 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0623. Min Act: -0.0006

Data Index: 992749 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0634. Min Act: -0.0006

Data Index: 560331 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0594. Min Act: -0.0005

Data Index: 342168 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0601. Min Act: -0.0006

Data Index: 967344 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0600. Min Act: -0.0006

Data Index: 970232 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0606. Min Act: -0.0006

Data Index: 548183 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0551. Min Act: -0.0006

Data Index: 1144590 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0588. Min Act: -0.0006

Data Index: 1202192 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0608. Min Act: -0.0006

Data Index: 1286261 (C4 (Web Text))

Max Activating Token Index: 663