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

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

Neuron 861 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0758. Min Act: -0.0004

Data Index: 1453227 (Python Code)

Max Activating Token Index: 320

Text #1

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0828. Min Act: -0.0004

Data Index: 1596320 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0714. Min Act: -0.0004

Data Index: 1367661 (Python Code)

Max Activating Token Index: 618

Text #3

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0749. Min Act: -0.0004

Data Index: 1436113 (Python Code)

Max Activating Token Index: 972

Text #4

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0718. Min Act: -0.0004

Data Index: 1512158 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0687. Min Act: -0.0004

Data Index: 1526497 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0738. Min Act: -0.0004

Data Index: 1375704 (Python Code)

Max Activating Token Index: 731

Text #7

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0748. Min Act: -0.0004

Data Index: 1535154 (Python Code)

Max Activating Token Index: 200

Text #8

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0705. Min Act: -0.0004

Data Index: 1542957 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0697. Min Act: -0.0004

Data Index: 1468255 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0682. Min Act: -0.0004

Data Index: 1493973 (Python Code)

Max Activating Token Index: 974

Text #11

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0710. Min Act: -0.0004

Data Index: 1453897 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0716. Min Act: -0.0004

Data Index: 1477867 (Python Code)

Max Activating Token Index: 139

Text #13

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0741. Min Act: -0.0004

Data Index: 1530346 (Python Code)

Max Activating Token Index: 365

Text #14

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0708. Min Act: -0.0004

Data Index: 1508992 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0733. Min Act: -0.0004

Data Index: 1556967 (Python Code)

Max Activating Token Index: 930

Text #16

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0660. Min Act: -0.0004

Data Index: 1384699 (Python Code)

Max Activating Token Index: 390

Text #17

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0664. Min Act: -0.0004

Data Index: 1443603 (Python Code)

Max Activating Token Index: 244

Text #18

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0631. Min Act: -0.0004

Data Index: 1514367 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0696. Min Act: -0.0004

Data Index: 1372070 (Python Code)

Max Activating Token Index: 182