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

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

Neuron 2498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1144193 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1123655 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0776. Min Act: -0.0001

Data Index: 274391 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0759. Min Act: -0.0001

Data Index: 68972 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1171290 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0765. Min Act: -0.0000

Data Index: 308980 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1507380 (Python Code)

Max Activating Token Index: 376

Text #7

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0727. Min Act: -0.0000

Data Index: 60394 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0711. Min Act: -0.0000

Data Index: 305258 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0654. Min Act: -0.0001

Data Index: 603197 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1074367 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1459568 (Python Code)

Max Activating Token Index: 1002

Text #12

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1255748 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0631. Min Act: -0.0000

Data Index: 507663 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1434512 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1454870 (Python Code)

Max Activating Token Index: 587

Text #16

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0599. Min Act: -0.0000

Data Index: 622424 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1110941 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0580. Min Act: -0.0000

Data Index: 112463 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0581. Min Act: -0.0000

Data Index: 643664 (C4 (Web Text))

Max Activating Token Index: 697