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

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

Neuron 2019 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: 1.2397. Min Range: -1.2397

Max Act: 1.2330. Min Act: -0.0000

Data Index: 596845 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.2397. Min Range: -1.2397

Max Act: 1.2397. Min Act: 0.0000

Data Index: 873370 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 1.2397. Min Range: -1.2397

Max Act: 1.0060. Min Act: 0.0000

Data Index: 1153759 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 1.2397. Min Range: -1.2397

Max Act: 1.0051. Min Act: -0.0000

Data Index: 264847 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.9966. Min Act: -0.0000

Data Index: 817074 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.9479. Min Act: 0.0000

Data Index: 1011687 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1189510 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.8436. Min Act: 0.0000

Data Index: 41985 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1081449 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7589. Min Act: 0.0000

Data Index: 998242 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1252678 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7128. Min Act: -0.0000

Data Index: 444374 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1124653 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7113. Min Act: 0.0000

Data Index: 501014 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1046612 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7055. Min Act: -0.0000

Data Index: 858696 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7351. Min Act: 0.0000

Data Index: 569258 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7182. Min Act: -0.0000

Data Index: 558923 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1157694 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.2397. Min Range: -1.2397

Max Act: 0.7100. Min Act: 0.0000

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 488