Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 328 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.5411. Min Act: -0.0000

Data Index: 788475 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.5546. Min Act: -0.0000

Data Index: 896748 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4784. Min Act: -0.0000

Data Index: 446233 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4366. Min Act: -0.0000

Data Index: 23250 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4238. Min Act: -0.0000

Data Index: 41488 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4145. Min Act: -0.0000

Data Index: 301737 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.4159. Min Act: 0.0000

Data Index: 531625 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3904. Min Act: -0.0000

Data Index: 493689 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3816. Min Act: -0.0000

Data Index: 665220 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3915. Min Act: -0.0000

Data Index: 397562 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3639. Min Act: -0.0000

Data Index: 372351 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3874. Min Act: 0.0001

Data Index: 851916 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3734. Min Act: -0.0000

Data Index: 443499 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1174626 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3529. Min Act: 0.0000

Data Index: 228544 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3617. Min Act: -0.0000

Data Index: 550092 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3574. Min Act: -0.0000

Data Index: 829196 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3438. Min Act: -0.0000

Data Index: 992866 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1190449 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.5546. Min Range: -0.5546

Max Act: 0.3167. Min Act: -0.0000

Data Index: 214138 (C4 (Web Text))

Max Activating Token Index: 1000