Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1717 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1206731 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0604. Min Act: -0.0002

Data Index: 594691 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1306490 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0601. Min Act: -0.0002

Data Index: 548606 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1321099 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1512335 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0502. Min Act: -0.0002

Data Index: 700663 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1054 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0588. Min Act: -0.0002

Data Index: 962338 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0579. Min Act: -0.0002

Data Index: 981679 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1225418 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0590. Min Act: -0.0002

Data Index: 964321 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0577. Min Act: -0.0002

Data Index: 38812 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0553. Min Act: -0.0002

Data Index: 730030 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0569. Min Act: -0.0002

Data Index: 546852 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0562. Min Act: -0.0002

Data Index: 350763 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0568. Min Act: -0.0002

Data Index: 627962 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1321681 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0522. Min Act: -0.0002

Data Index: 31346 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1626 (C4 (Web Text))

Max Activating Token Index: 353