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

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

Neuron 807 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.7340. Min Act: -0.0000

Data Index: 800251 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.7615. Min Act: -0.0000

Data Index: 271804 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6491. Min Act: -0.0000

Data Index: 92302 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6118. Min Act: -0.0000

Data Index: 183705 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1134320 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5492. Min Act: -0.0000

Data Index: 667032 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6149. Min Act: -0.0000

Data Index: 685655 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6144. Min Act: -0.0000

Data Index: 599625 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6321. Min Act: -0.0000

Data Index: 341425 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5736. Min Act: -0.0000

Data Index: 303667 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6173. Min Act: -0.0000

Data Index: 212517 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1077218 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5573. Min Act: -0.0000

Data Index: 365352 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5753. Min Act: -0.0000

Data Index: 393639 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5722. Min Act: -0.0000

Data Index: 356830 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1016736 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5433. Min Act: -0.0000

Data Index: 220119 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5562. Min Act: -0.0000

Data Index: 764439 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5551. Min Act: -0.0000

Data Index: 918403 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5746. Min Act: -0.0000

Data Index: 593425 (C4 (Web Text))

Max Activating Token Index: 871