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

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

Neuron 1695 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: 0.9741. Min Range: -0.9741

Max Act: 0.8876. Min Act: -0.0001

Data Index: 1402055 (Python Code)

Max Activating Token Index: 254

Text #1

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9479. Min Act: -0.0001

Data Index: 1411633 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9741. Min Act: -0.0001

Data Index: 1400761 (Python Code)

Max Activating Token Index: 49

Text #3

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8772. Min Act: -0.0001

Data Index: 1647253 (Python Code)

Max Activating Token Index: 778

Text #4

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1437921 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8613. Min Act: -0.0001

Data Index: 1475318 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7661. Min Act: -0.0001

Data Index: 1405213 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7734. Min Act: -0.0001

Data Index: 1499795 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8302. Min Act: -0.0001

Data Index: 1419699 (Python Code)

Max Activating Token Index: 540

Text #9

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1597483 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8009. Min Act: -0.0001

Data Index: 1508446 (Python Code)

Max Activating Token Index: 141

Text #11

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9068. Min Act: -0.0001

Data Index: 1403788 (Python Code)

Max Activating Token Index: 843

Text #12

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7113. Min Act: -0.0001

Data Index: 1470044 (Python Code)

Max Activating Token Index: 598

Text #13

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8050. Min Act: -0.0001

Data Index: 1421955 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7772. Min Act: -0.0001

Data Index: 1594096 (Python Code)

Max Activating Token Index: 486

Text #15

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7290. Min Act: -0.0001

Data Index: 1480360 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8289. Min Act: -0.0001

Data Index: 1602546 (Python Code)

Max Activating Token Index: 889

Text #17

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7884. Min Act: -0.0001

Data Index: 1391955 (Python Code)

Max Activating Token Index: 879

Text #18

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1618903 (Python Code)

Max Activating Token Index: 599

Text #19

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7733. Min Act: -0.0001

Data Index: 1644999 (Python Code)

Max Activating Token Index: 502