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

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

Neuron 4430 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.9859. Min Act: -0.0000

Data Index: 457324 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 1.0109. Min Range: -1.0109

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1219739 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1313203 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.9101. Min Act: -0.0000

Data Index: 475408 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8962. Min Act: -0.0000

Data Index: 710160 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1149796 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8000. Min Act: -0.0000

Data Index: 742178 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.5889. Min Act: -0.0000

Data Index: 741149 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1203837 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.5248. Min Act: -0.0000

Data Index: 490768 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.5087. Min Act: -0.0000

Data Index: 485920 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.5215. Min Act: -0.0000

Data Index: 318259 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.4766. Min Act: -0.0000

Data Index: 967025 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1333817 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1160620 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1225538 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.4698. Min Act: -0.0000

Data Index: 425287 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.4363. Min Act: -0.0000

Data Index: 988191 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.4824. Min Act: -0.0000

Data Index: 356543 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.4794. Min Act: -0.0000

Data Index: 848109 (C4 (Web Text))

Max Activating Token Index: 547