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

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

Neuron 3786 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: 0.5506. Min Range: -0.5506

Max Act: 0.4995. Min Act: -0.0000

Data Index: 492723 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1206317 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5506. Min Act: -0.0000

Data Index: 408932 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5219. Min Act: -0.0000

Data Index: 827114 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4853. Min Act: -0.0000

Data Index: 616882 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4648. Min Act: -0.0000

Data Index: 833749 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4614. Min Act: -0.0000

Data Index: 40341 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4317. Min Act: -0.0000

Data Index: 133084 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4072. Min Act: -0.0000

Data Index: 712633 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4172. Min Act: -0.0000

Data Index: 925464 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.3938. Min Act: -0.0000

Data Index: 105862 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.3869. Min Act: -0.0000

Data Index: 730612 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1068112 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.3509. Min Act: -0.0000

Data Index: 789694 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.3309. Min Act: -0.0000

Data Index: 767492 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.3182. Min Act: -0.0000

Data Index: 432045 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.2761. Min Act: -0.0000

Data Index: 634689 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.2795. Min Act: -0.0000

Data Index: 347276 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1278545 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1044577 (C4 (Web Text))

Max Activating Token Index: 823