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

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

Neuron 1351 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: 0.6006. Min Range: -0.6006

Max Act: 0.6006. Min Act: -0.0000

Data Index: 42296 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5579. Min Act: -0.0000

Data Index: 703562 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5541. Min Act: -0.0000

Data Index: 745214 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5480. Min Act: -0.0000

Data Index: 349027 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4937. Min Act: -0.0000

Data Index: 592215 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5528. Min Act: -0.0000

Data Index: 989248 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5560. Min Act: -0.0000

Data Index: 264965 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1189216 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5197. Min Act: -0.0000

Data Index: 640515 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1147957 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5400. Min Act: -0.0000

Data Index: 736851 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4989. Min Act: -0.0000

Data Index: 420055 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5148. Min Act: -0.0000

Data Index: 489927 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1192926 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4121. Min Act: -0.0000

Data Index: 124047 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4404. Min Act: -0.0000

Data Index: 925155 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4538. Min Act: -0.0000

Data Index: 673239 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4765. Min Act: -0.0000

Data Index: 729493 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4869. Min Act: -0.0000

Data Index: 778442 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4385. Min Act: -0.0000

Data Index: 401629 (C4 (Web Text))

Max Activating Token Index: 337