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

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

Neuron 4996 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: 5.2003. Min Range: -5.2003

Max Act: 5.2003. Min Act: -0.0000

Data Index: 627468 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.5728. Min Act: -0.0000

Data Index: 425971 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.3160. Min Act: -0.0000

Data Index: 392404 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.7958. Min Act: -0.0000

Data Index: 1093487 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.2277. Min Act: -0.0000

Data Index: 780332 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.2010. Min Act: -0.0000

Data Index: 598088 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.2594. Min Act: -0.0000

Data Index: 112365 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.0853. Min Act: -0.0000

Data Index: 709895 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.0868. Min Act: -0.0000

Data Index: 293594 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.2288. Min Act: -0.0000

Data Index: 864885 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 5.2003. Min Range: -5.2003

Max Act: 3.8598. Min Act: -0.0000

Data Index: 1200460 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.0501. Min Act: -0.0000

Data Index: 553040 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 5.2003. Min Range: -5.2003

Max Act: 3.6851. Min Act: -0.0000

Data Index: 591539 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 5.2003. Min Range: -5.2003

Max Act: 3.6607. Min Act: -0.0000

Data Index: 1211433 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.0056. Min Act: -0.0000

Data Index: 680982 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 5.2003. Min Range: -5.2003

Max Act: 3.8303. Min Act: -0.0000

Data Index: 744474 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 5.2003. Min Range: -5.2003

Max Act: 4.3449. Min Act: -0.0000

Data Index: 1098428 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 5.2003. Min Range: -5.2003

Max Act: 3.9439. Min Act: -0.0000

Data Index: 434422 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 5.2003. Min Range: -5.2003

Max Act: 3.9645. Min Act: -0.0000

Data Index: 987305 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 5.2003. Min Range: -5.2003

Max Act: 3.8743. Min Act: -0.0000

Data Index: 796988 (C4 (Web Text))

Max Activating Token Index: 869