Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4447 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0344. Min Range: -1.0344

Max Act: 1.0344. Min Act: 0.0000

Data Index: 875233 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.9609. Min Act: -0.0000

Data Index: 456490 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.9538. Min Act: -0.0000

Data Index: 114997 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.8170. Min Act: -0.0000

Data Index: 373224 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7662. Min Act: -0.0000

Data Index: 692616 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1187754 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7880. Min Act: -0.0000

Data Index: 430105 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1256911 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1063547 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7169. Min Act: -0.0000

Data Index: 664436 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1108040 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1359393 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6699. Min Act: -0.0000

Data Index: 719919 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6662. Min Act: -0.0000

Data Index: 566262 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6391. Min Act: 0.0000

Data Index: 522014 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1057287 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6104. Min Act: -0.0000

Data Index: 107864 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6102. Min Act: -0.0000

Data Index: 831366 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6069. Min Act: -0.0000

Data Index: 207526 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1073395 (C4 (Web Text))

Max Activating Token Index: 68