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

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

Neuron 4502 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: 2.9460. Min Range: -2.9460

Max Act: 2.9460. Min Act: -0.0000

Data Index: 1040126 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.6702. Min Act: -0.0000

Data Index: 156426 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.5290. Min Act: -0.0000

Data Index: 742297 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.6602. Min Act: -0.0000

Data Index: 675165 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.5841. Min Act: -0.0000

Data Index: 793236 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.2549. Min Act: -0.0000

Data Index: 1289287 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.1917. Min Act: -0.0000

Data Index: 163531 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.3035. Min Act: -0.0000

Data Index: 386665 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.2848. Min Act: -0.0000

Data Index: 33767 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.2832. Min Act: -0.0000

Data Index: 78200 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.1428. Min Act: -0.0000

Data Index: 401081 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.0258. Min Act: -0.0000

Data Index: 1211810 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.1193. Min Act: -0.0000

Data Index: 536057 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.0092. Min Act: -0.0000

Data Index: 1174449 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.2336. Min Act: -0.0000

Data Index: 626872 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 2.9460. Min Range: -2.9460

Max Act: 1.9967. Min Act: -0.0000

Data Index: 1018380 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 2.9460. Min Range: -2.9460

Max Act: 1.8760. Min Act: -0.0000

Data Index: 627561 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 2.9460. Min Range: -2.9460

Max Act: 1.9874. Min Act: -0.0000

Data Index: 42379 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.1005. Min Act: -0.0000

Data Index: 1024793 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 2.9460. Min Range: -2.9460

Max Act: 2.0974. Min Act: -0.0000

Data Index: 886812 (C4 (Web Text))

Max Activating Token Index: 490