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

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

Neuron 951 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: 0.8516. Min Range: -0.8516

Max Act: 0.8516. Min Act: -0.0001

Data Index: 452483 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7993. Min Act: -0.0001

Data Index: 555004 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7396. Min Act: -0.0001

Data Index: 171916 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7728. Min Act: -0.0000

Data Index: 71114 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7627. Min Act: -0.0000

Data Index: 648611 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7329. Min Act: -0.0001

Data Index: 18361 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7237. Min Act: -0.0001

Data Index: 741141 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6564. Min Act: -0.0001

Data Index: 535578 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1093663 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7006. Min Act: -0.0000

Data Index: 357014 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7055. Min Act: -0.0000

Data Index: 300830 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7019. Min Act: -0.0001

Data Index: 871081 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6740. Min Act: -0.0001

Data Index: 961729 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6938. Min Act: -0.0000

Data Index: 936961 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6888. Min Act: -0.0001

Data Index: 1086333 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6880. Min Act: -0.0001

Data Index: 177304 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6977. Min Act: -0.0001

Data Index: 1180638 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6934. Min Act: -0.0000

Data Index: 220519 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6657. Min Act: -0.0001

Data Index: 846388 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6838. Min Act: -0.0000

Data Index: 318515 (C4 (Web Text))

Max Activating Token Index: 47