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

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

Neuron 4494 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: 0.0721. Min Range: -0.0721

Max Act: 0.0721. Min Act: -0.0000

Data Index: 644747 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0619. Min Act: -0.0000

Data Index: 1415580 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1528545 (Python Code)

Max Activating Token Index: 536

Text #3

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1422976 (Python Code)

Max Activating Token Index: 709

Text #4

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1624248 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1650120 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0648. Min Act: -0.0000

Data Index: 791653 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1603389 (Python Code)

Max Activating Token Index: 580

Text #8

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1098112 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1640490 (Python Code)

Max Activating Token Index: 390

Text #10

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1473723 (Python Code)

Max Activating Token Index: 960

Text #11

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1009294 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1056033 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0551. Min Act: -0.0000

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1374211 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1116365 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1048527 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0514. Min Act: -0.0000

Data Index: 484259 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1611827 (Python Code)

Max Activating Token Index: 477

Text #19

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1362490 (Python Code)

Max Activating Token Index: 268