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

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

Neuron 2509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.8257. Min Act: -0.0001

Data Index: 1530158 (Python Code)

Max Activating Token Index: 905

Text #1

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7950. Min Act: -0.0001

Data Index: 1588895 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1485662 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7610. Min Act: -0.0001

Data Index: 1508578 (Python Code)

Max Activating Token Index: 821

Text #4

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.8432. Min Act: -0.0001

Data Index: 1567414 (Python Code)

Max Activating Token Index: 923

Text #5

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1573410 (Python Code)

Max Activating Token Index: 785

Text #6

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7745. Min Act: -0.0001

Data Index: 1408390 (Python Code)

Max Activating Token Index: 940

Text #7

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7925. Min Act: -0.0001

Data Index: 1399598 (Python Code)

Max Activating Token Index: 738

Text #8

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1480741 (Python Code)

Max Activating Token Index: 775

Text #9

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.8081. Min Act: -0.0001

Data Index: 1480050 (Python Code)

Max Activating Token Index: 834

Text #10

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7872. Min Act: -0.0001

Data Index: 1557672 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1546930 (Python Code)

Max Activating Token Index: 910

Text #12

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7487. Min Act: -0.0001

Data Index: 1469141 (Python Code)

Max Activating Token Index: 684

Text #13

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7343. Min Act: -0.0001

Data Index: 1424763 (Python Code)

Max Activating Token Index: 732

Text #14

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.8037. Min Act: -0.0001

Data Index: 1409931 (Python Code)

Max Activating Token Index: 882

Text #15

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7532. Min Act: -0.0001

Data Index: 1441131 (Python Code)

Max Activating Token Index: 967

Text #16

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7739. Min Act: -0.0001

Data Index: 1520785 (Python Code)

Max Activating Token Index: 585

Text #17

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1621084 (Python Code)

Max Activating Token Index: 713

Text #18

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7669. Min Act: -0.0001

Data Index: 1375076 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 0.8432. Min Range: -0.8432

Max Act: 0.7331. Min Act: -0.0001

Data Index: 1435290 (Python Code)

Max Activating Token Index: 761