Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 164 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1640120 (Python Code)

Max Activating Token Index: 879

Text #1

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1522223 (Python Code)

Max Activating Token Index: 355

Text #2

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0702. Min Act: -0.0003

Data Index: 508716 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0712. Min Act: -0.0003

Data Index: 1371664 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0679. Min Act: -0.0003

Data Index: 1544364 (Python Code)

Max Activating Token Index: 115

Text #5

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1360981 (Python Code)

Max Activating Token Index: 264

Text #6

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1406743 (Python Code)

Max Activating Token Index: 1017

Text #7

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1426627 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0668. Min Act: -0.0003

Data Index: 993505 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1556450 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1423405 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1442032 (Python Code)

Max Activating Token Index: 331

Text #12

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1466374 (Python Code)

Max Activating Token Index: 917

Text #13

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1479216 (Python Code)

Max Activating Token Index: 770

Text #14

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1226384 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1394199 (Python Code)

Max Activating Token Index: 515

Text #16

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0595. Min Act: -0.0003

Data Index: 178187 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1516712 (Python Code)

Max Activating Token Index: 879

Text #18

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1531000 (Python Code)

Max Activating Token Index: 334

Text #19

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1034894 (C4 (Web Text))

Max Activating Token Index: 31