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

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

Neuron 483 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7903. Min Act: -0.0000

Data Index: 264182 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7304. Min Act: -0.0000

Data Index: 485632 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6990. Min Act: -0.0000

Data Index: 643629 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6420. Min Act: -0.0000

Data Index: 800566 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1169126 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.5609. Min Act: -0.0000

Data Index: 70279 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1135928 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6392. Min Act: -0.0000

Data Index: 727175 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6068. Min Act: -0.0000

Data Index: 742252 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4774. Min Act: -0.0000

Data Index: 456853 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4446. Min Act: -0.0000

Data Index: 73716 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.3891. Min Act: -0.0000

Data Index: 805790 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.3983. Min Act: -0.0000

Data Index: 121877 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.3700. Min Act: -0.0000

Data Index: 982274 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.3924. Min Act: -0.0000

Data Index: 343293 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.3507. Min Act: -0.0000

Data Index: 905450 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.3393. Min Act: -0.0000

Data Index: 288376 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.3504. Min Act: -0.0000

Data Index: 902927 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1201131 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1248341 (C4 (Web Text))

Max Activating Token Index: 767