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

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

Neuron 1632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.5838. Min Range: -6.5838

Max Act: 6.5838. Min Act: -0.0000

Data Index: 150363 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.9461. Min Act: -0.0000

Data Index: 894424 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 6.5838. Min Range: -6.5838

Max Act: 6.2216. Min Act: -0.0000

Data Index: 1286720 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.8387. Min Act: -0.0000

Data Index: 1019398 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.6070. Min Act: -0.0000

Data Index: 733931 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.5680. Min Act: -0.0000

Data Index: 590349 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.6361. Min Act: -0.0000

Data Index: 207292 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.6384. Min Act: -0.0000

Data Index: 759775 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.4676. Min Act: -0.0000

Data Index: 792227 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.2825. Min Act: -0.0000

Data Index: 1280777 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.1654. Min Act: -0.0000

Data Index: 599217 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.2102. Min Act: -0.0000

Data Index: 1001198 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.3318. Min Act: -0.0000

Data Index: 384992 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.5387. Min Act: -0.0000

Data Index: 1314673 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.2145. Min Act: -0.0000

Data Index: 716162 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.5669. Min Act: -0.0000

Data Index: 1167219 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.0231. Min Act: -0.0000

Data Index: 277606 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.1096. Min Act: -0.0000

Data Index: 434642 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.0955. Min Act: -0.0000

Data Index: 1302857 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 6.5838. Min Range: -6.5838

Max Act: 5.0669. Min Act: -0.0000

Data Index: 354140 (C4 (Web Text))

Max Activating Token Index: 107