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

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

Neuron 2012 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.4151. Min Act: -0.0000

Data Index: 748719 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.2631. Min Act: -0.0000

Data Index: 606787 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0419. Min Act: -0.0000

Data Index: 112201 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0424. Min Act: -0.0000

Data Index: 579300 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1343759 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1306198 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9194. Min Act: -0.0000

Data Index: 826782 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9233. Min Act: -0.0000

Data Index: 376770 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9195. Min Act: -0.0000

Data Index: 214552 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9538. Min Act: -0.0000

Data Index: 413861 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9602. Min Act: -0.0000

Data Index: 188821 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9019. Min Act: -0.0000

Data Index: 1203249 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.8829. Min Act: -0.0000

Data Index: 561418 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9059. Min Act: -0.0000

Data Index: 286463 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.8980. Min Act: -0.0000

Data Index: 207072 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1192438 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.8745. Min Act: -0.0000

Data Index: 766927 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.8742. Min Act: -0.0000

Data Index: 104034 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.8624. Min Act: -0.0000

Data Index: 764882 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.8260. Min Act: -0.0000

Data Index: 480799 (C4 (Web Text))

Max Activating Token Index: 537