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

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

Neuron 4950 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.7670. Min Act: -0.0001

Data Index: 284037 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6875. Min Act: -0.0001

Data Index: 1249689 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6113. Min Act: -0.0001

Data Index: 855994 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5980. Min Act: -0.0001

Data Index: 491344 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6000. Min Act: -0.0001

Data Index: 839676 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5867. Min Act: -0.0001

Data Index: 683399 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5460. Min Act: -0.0001

Data Index: 394797 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5580. Min Act: -0.0001

Data Index: 499428 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5238. Min Act: -0.0001

Data Index: 952310 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5410. Min Act: -0.0001

Data Index: 616580 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5394. Min Act: -0.0001

Data Index: 78567 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5231. Min Act: -0.0001

Data Index: 735720 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4982. Min Act: -0.0001

Data Index: 1058749 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5171. Min Act: -0.0001

Data Index: 330201 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5093. Min Act: -0.0001

Data Index: 187143 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4982. Min Act: -0.0001

Data Index: 34555 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4826. Min Act: -0.0001

Data Index: 333039 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4786. Min Act: -0.0001

Data Index: 524902 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5373. Min Act: -0.0001

Data Index: 411725 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5034. Min Act: -0.0001

Data Index: 148478 (C4 (Web Text))

Max Activating Token Index: 649