Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1255 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0727. Min Act: -0.0002

Data Index: 3973 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1637839 (Python Code)

Max Activating Token Index: 377

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0695. Min Act: -0.0002

Data Index: 317391 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1645429 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0648. Min Act: -0.0001

Data Index: 453640 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0692. Min Act: -0.0001

Data Index: 105503 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0709. Min Act: -0.0001

Data Index: 589807 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0637. Min Act: -0.0002

Data Index: 252029 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1440795 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1410899 (Python Code)

Max Activating Token Index: 1021

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0627. Min Act: -0.0001

Data Index: 278241 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0619. Min Act: -0.0001

Data Index: 617496 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1406353 (Python Code)

Max Activating Token Index: 923

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1427284 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1291430 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0566. Min Act: -0.0002

Data Index: 493047 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1434773 (Python Code)

Max Activating Token Index: 638

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0605. Min Act: -0.0001

Data Index: 616400 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1159277 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0651. Min Act: -0.0002

Data Index: 974764 (C4 (Web Text))

Max Activating Token Index: 307