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

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

Neuron 3790 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0000

Data Index: 852161 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1300709 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0748. Min Act: -0.0000

Data Index: 548605 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1505113 (Python Code)

Max Activating Token Index: 376

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0650. Min Act: -0.0000

Data Index: 804684 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1433958 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0656. Min Act: -0.0000

Data Index: 912000 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0608. Min Act: -0.0000

Data Index: 597435 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1067154 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0564. Min Act: -0.0000

Data Index: 548419 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1400004 (Python Code)

Max Activating Token Index: 94

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0574. Min Act: -0.0000

Data Index: 87159 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0556. Min Act: -0.0000

Data Index: 210256 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1518784 (Python Code)

Max Activating Token Index: 842

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0568. Min Act: -0.0000

Data Index: 464653 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0570. Min Act: -0.0000

Data Index: 367604 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0588. Min Act: -0.0000

Data Index: 590876 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0566. Min Act: -0.0000

Data Index: 518215 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0559. Min Act: -0.0000

Data Index: 734261 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1290078 (C4 (Web Text))

Max Activating Token Index: 324