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

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

Neuron 2038 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0852. Min Range: -1.0852

Max Act: 1.0852. Min Act: -0.0000

Data Index: 64060 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1069012 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1202000 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8643. Min Act: -0.0000

Data Index: 686526 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8138. Min Act: 0.0000

Data Index: 535033 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8009. Min Act: -0.0000

Data Index: 961842 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8336. Min Act: -0.0000

Data Index: 408009 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8008. Min Act: -0.0000

Data Index: 531522 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7786. Min Act: -0.0000

Data Index: 763032 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1324337 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7245. Min Act: -0.0000

Data Index: 228789 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1008761 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7466. Min Act: -0.0000

Data Index: 908288 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7505. Min Act: -0.0000

Data Index: 48703 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7178. Min Act: -0.0000

Data Index: 550400 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7396. Min Act: -0.0000

Data Index: 608054 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7581. Min Act: -0.0000

Data Index: 305127 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7257. Min Act: -0.0000

Data Index: 418307 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7205. Min Act: -0.0000

Data Index: 637724 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.6726. Min Act: -0.0000

Data Index: 719759 (C4 (Web Text))

Max Activating Token Index: 683