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

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

Neuron 2694 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: 1.9804. Min Range: -1.9804

Max Act: 1.9804. Min Act: -0.0000

Data Index: 1347648 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.8878. Min Act: -0.0000

Data Index: 584475 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7341. Min Act: -0.0000

Data Index: 1034681 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.8032. Min Act: -0.0000

Data Index: 1355185 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.6229. Min Act: -0.0000

Data Index: 607881 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.6029. Min Act: -0.0000

Data Index: 284909 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.4925. Min Act: -0.0000

Data Index: 1207962 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.4594. Min Act: -0.0000

Data Index: 534928 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.4546. Min Act: -0.0000

Data Index: 194795 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1029229 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.5194. Min Act: -0.0000

Data Index: 242807 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.5223. Min Act: -0.0000

Data Index: 257160 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1039801 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.5068. Min Act: -0.0000

Data Index: 920363 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1285202 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1328143 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.5562. Min Act: -0.0000

Data Index: 161833 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.3788. Min Act: -0.0000

Data Index: 331324 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.4531. Min Act: -0.0000

Data Index: 701788 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.3612. Min Act: -0.0000

Data Index: 237442 (C4 (Web Text))

Max Activating Token Index: 90