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

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

Neuron 3136 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.9837. Min Act: -0.0000

Data Index: 77261 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.9003. Min Act: -0.0000

Data Index: 956714 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8332. Min Act: -0.0000

Data Index: 453280 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1346501 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8503. Min Act: -0.0000

Data Index: 624349 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8205. Min Act: -0.0000

Data Index: 982800 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1246289 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.8013. Min Act: 0.0000

Data Index: 1188423 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7999. Min Act: -0.0000

Data Index: 899039 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1106216 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7625. Min Act: -0.0000

Data Index: 819594 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7752. Min Act: -0.0000

Data Index: 890230 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7721. Min Act: -0.0000

Data Index: 203159 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7235. Min Act: -0.0000

Data Index: 407318 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7628. Min Act: -0.0000

Data Index: 737202 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7501. Min Act: -0.0000

Data Index: 859331 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1248214 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7373. Min Act: -0.0000

Data Index: 638437 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1141743 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.9837. Min Range: -0.9837

Max Act: 0.7072. Min Act: -0.0000

Data Index: 951462 (C4 (Web Text))

Max Activating Token Index: 865