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

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

Neuron 2778 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: 1.5061. Min Range: -1.5061

Max Act: 1.5061. Min Act: -0.0000

Data Index: 713465 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.1922. Min Act: -0.0000

Data Index: 1101023 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.1906. Min Act: -0.0000

Data Index: 411211 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0886. Min Act: -0.0000

Data Index: 537415 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0830. Min Act: -0.0000

Data Index: 73829 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.1275. Min Act: -0.0000

Data Index: 736200 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.1136. Min Act: -0.0000

Data Index: 645644 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0580. Min Act: -0.0000

Data Index: 250764 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0852. Min Act: -0.0000

Data Index: 674762 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0023. Min Act: -0.0000

Data Index: 325931 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0150. Min Act: -0.0000

Data Index: 126794 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0420. Min Act: -0.0000

Data Index: 801885 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.5061. Min Range: -1.5061

Max Act: 0.9991. Min Act: -0.0000

Data Index: 368163 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1051398 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0193. Min Act: -0.0000

Data Index: 80220 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0466. Min Act: -0.0000

Data Index: 679773 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0208. Min Act: -0.0000

Data Index: 722960 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 1.5061. Min Range: -1.5061

Max Act: 0.9536. Min Act: -0.0000

Data Index: 612217 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.0056. Min Act: -0.0000

Data Index: 224258 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 1.5061. Min Range: -1.5061

Max Act: 0.9433. Min Act: -0.0000

Data Index: 380353 (C4 (Web Text))

Max Activating Token Index: 43