Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3452 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.4686. Min Range: -6.4686

Max Act: 6.4686. Min Act: -0.0000

Data Index: 1337772 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 6.4686. Min Range: -6.4686

Max Act: 5.6172. Min Act: -0.0000

Data Index: 1148094 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 6.4686. Min Range: -6.4686

Max Act: 4.9619. Min Act: -0.0000

Data Index: 792844 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 6.4686. Min Range: -6.4686

Max Act: 4.7068. Min Act: -0.0000

Data Index: 220998 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 6.4686. Min Range: -6.4686

Max Act: 4.7982. Min Act: -0.0000

Data Index: 166839 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 6.4686. Min Range: -6.4686

Max Act: 4.8000. Min Act: -0.0000

Data Index: 351677 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 6.4686. Min Range: -6.4686

Max Act: 4.7075. Min Act: -0.0000

Data Index: 1179422 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 6.4686. Min Range: -6.4686

Max Act: 4.6012. Min Act: -0.0000

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 6.4686. Min Range: -6.4686

Max Act: 4.5553. Min Act: -0.0000

Data Index: 1188642 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 6.4686. Min Range: -6.4686

Max Act: 4.5762. Min Act: -0.0000

Data Index: 988689 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 6.4686. Min Range: -6.4686

Max Act: 3.9617. Min Act: -0.0000

Data Index: 121356 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 6.4686. Min Range: -6.4686

Max Act: 3.9757. Min Act: -0.0000

Data Index: 437040 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 6.4686. Min Range: -6.4686

Max Act: 4.1430. Min Act: -0.0000

Data Index: 1107578 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 6.4686. Min Range: -6.4686

Max Act: 3.8654. Min Act: -0.0000

Data Index: 343792 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 6.4686. Min Range: -6.4686

Max Act: 3.8072. Min Act: -0.0000

Data Index: 711529 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 6.4686. Min Range: -6.4686

Max Act: 3.9424. Min Act: -0.0000

Data Index: 827259 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 6.4686. Min Range: -6.4686

Max Act: 3.7044. Min Act: -0.0000

Data Index: 399526 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 6.4686. Min Range: -6.4686

Max Act: 3.8452. Min Act: -0.0000

Data Index: 486178 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 6.4686. Min Range: -6.4686

Max Act: 3.7936. Min Act: -0.0000

Data Index: 661527 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 6.4686. Min Range: -6.4686

Max Act: 3.7871. Min Act: -0.0000

Data Index: 70237 (C4 (Web Text))

Max Activating Token Index: 557