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

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

Neuron 3918 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0420. Min Range: -5.0420

Max Act: 5.0420. Min Act: -0.0000

Data Index: 354746 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.5375. Min Act: -0.0000

Data Index: 683350 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.9939. Min Act: -0.0000

Data Index: 704406 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.1233. Min Act: -0.0000

Data Index: 574284 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.1796. Min Act: -0.0000

Data Index: 280143 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.9370. Min Act: -0.0000

Data Index: 860895 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.6964. Min Act: -0.0000

Data Index: 124041 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.6321. Min Act: -0.0000

Data Index: 782059 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.8891. Min Act: -0.0000

Data Index: 899839 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.8427. Min Act: -0.0000

Data Index: 288160 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.7226. Min Act: -0.0001

Data Index: 1178763 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.5613. Min Act: -0.0001

Data Index: 42681 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.6289. Min Act: -0.0000

Data Index: 533737 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.4236. Min Act: -0.0001

Data Index: 1286463 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.5440. Min Act: -0.0001

Data Index: 979253 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.5724. Min Act: -0.0000

Data Index: 677761 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.3599. Min Act: -0.0000

Data Index: 969462 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.1849. Min Act: -0.0001

Data Index: 772504 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.1717. Min Act: -0.0000

Data Index: 675362 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 5.0420. Min Range: -5.0420

Max Act: 3.2877. Min Act: -0.0000

Data Index: 1053968 (C4 (Web Text))

Max Activating Token Index: 504