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

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

Neuron 4899 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5357. Min Range: -4.5357

Max Act: 4.5357. Min Act: -0.0001

Data Index: 428120 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 4.5357. Min Range: -4.5357

Max Act: 4.2715. Min Act: -0.0000

Data Index: 653357 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 4.5357. Min Range: -4.5357

Max Act: 4.3731. Min Act: -0.0000

Data Index: 1114784 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.9276. Min Act: -0.0000

Data Index: 78998 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.9084. Min Act: -0.0000

Data Index: 395680 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 4.5357. Min Range: -4.5357

Max Act: 4.0397. Min Act: -0.0000

Data Index: 759726 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 4.5357. Min Range: -4.5357

Max Act: 4.0339. Min Act: -0.0000

Data Index: 1267916 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.7928. Min Act: -0.0000

Data Index: 1248312 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 4.5357. Min Range: -4.5357

Max Act: 4.1299. Min Act: -0.0000

Data Index: 457202 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.9644. Min Act: -0.0000

Data Index: 952628 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.4252. Min Act: -0.0001

Data Index: 779098 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.8826. Min Act: -0.0000

Data Index: 345109 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 4.5357. Min Range: -4.5357

Max Act: 4.0278. Min Act: -0.0000

Data Index: 1311883 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 4.5357. Min Range: -4.5357

Max Act: 4.0115. Min Act: -0.0000

Data Index: 714804 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.9508. Min Act: -0.0000

Data Index: 1085931 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.7850. Min Act: -0.0000

Data Index: 149462 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.6058. Min Act: -0.0000

Data Index: 876732 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.7694. Min Act: -0.0000

Data Index: 977810 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.4601. Min Act: -0.0000

Data Index: 656897 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 4.5357. Min Range: -4.5357

Max Act: 3.6011. Min Act: -0.0000

Data Index: 424026 (C4 (Web Text))

Max Activating Token Index: 621