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

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

Neuron 1201 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6215. Min Act: -0.0001

Data Index: 1491942 (Python Code)

Max Activating Token Index: 258

Text #1

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.7148. Min Act: -0.0001

Data Index: 1648168 (Python Code)

Max Activating Token Index: 185

Text #2

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5568. Min Act: -0.0001

Data Index: 499428 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5670. Min Act: -0.0000

Data Index: 103142 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6416. Min Act: -0.0001

Data Index: 57299 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5244. Min Act: -0.0001

Data Index: 321345 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5582. Min Act: -0.0001

Data Index: 451626 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5284. Min Act: -0.0001

Data Index: 389557 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5293. Min Act: -0.0001

Data Index: 34665 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.4694. Min Act: -0.0001

Data Index: 442333 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5013. Min Act: -0.0001

Data Index: 636912 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5166. Min Act: -0.0001

Data Index: 1157474 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.4807. Min Act: -0.0000

Data Index: 374010 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5007. Min Act: -0.0001

Data Index: 157421 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.4762. Min Act: -0.0001

Data Index: 910899 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.4293. Min Act: -0.0001

Data Index: 335693 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1234325 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.4478. Min Act: -0.0000

Data Index: 691025 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.4802. Min Act: -0.0001

Data Index: 855204 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.4620. Min Act: -0.0001

Data Index: 1593581 (Python Code)

Max Activating Token Index: 291