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

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

Neuron 1263 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: 0.8466. Min Range: -0.8466

Max Act: 0.8466. Min Act: -0.0000

Data Index: 432416 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7950. Min Act: -0.0000

Data Index: 285192 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7046. Min Act: -0.0000

Data Index: 419982 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6762. Min Act: -0.0000

Data Index: 225009 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6929. Min Act: -0.0000

Data Index: 215495 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6201. Min Act: -0.0000

Data Index: 861037 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6896. Min Act: -0.0000

Data Index: 76619 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7281. Min Act: -0.0000

Data Index: 853064 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6776. Min Act: -0.0000

Data Index: 999339 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6366. Min Act: -0.0000

Data Index: 854833 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1352211 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6223. Min Act: -0.0000

Data Index: 440817 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6089. Min Act: -0.0000

Data Index: 516135 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6106. Min Act: -0.0000

Data Index: 777759 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6046. Min Act: -0.0001

Data Index: 866764 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1015322 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6219. Min Act: -0.0000

Data Index: 336372 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6356. Min Act: -0.0000

Data Index: 254504 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6202. Min Act: -0.0000

Data Index: 248682 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6156. Min Act: -0.0000

Data Index: 985360 (C4 (Web Text))

Max Activating Token Index: 943