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

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

Neuron 217 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.7752. Min Act: -0.0000

Data Index: 635146 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.6913. Min Act: -0.0000

Data Index: 128985 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.7201. Min Act: -0.0000

Data Index: 288004 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.7138. Min Act: -0.0000

Data Index: 636389 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.6914. Min Act: -0.0000

Data Index: 90069 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.7031. Min Act: -0.0000

Data Index: 553714 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.5782. Min Act: -0.0000

Data Index: 1280852 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.6102. Min Act: -0.0000

Data Index: 912037 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.6081. Min Act: -0.0000

Data Index: 286379 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.6688. Min Act: -0.0000

Data Index: 293920 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.5716. Min Act: -0.0000

Data Index: 214770 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.5573. Min Act: -0.0000

Data Index: 1034393 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.4998. Min Act: -0.0000

Data Index: 781688 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.5386. Min Act: -0.0000

Data Index: 904399 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.4910. Min Act: -0.0000

Data Index: 842889 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.5188. Min Act: -0.0000

Data Index: 1024205 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1244589 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.4950. Min Act: -0.0000

Data Index: 967193 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.5011. Min Act: -0.0000

Data Index: 757768 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.4501. Min Act: -0.0000

Data Index: 244155 (C4 (Web Text))

Max Activating Token Index: 982