Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1229 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1358. Min Act: -0.0002

Data Index: 1239004 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1173725 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1173440 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1030. Min Act: -0.0001

Data Index: 775238 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1074. Min Act: -0.0001

Data Index: 291384 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1116. Min Act: -0.0001

Data Index: 766573 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1175. Min Act: -0.0001

Data Index: 460391 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1349526 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1042. Min Act: -0.0001

Data Index: 292908 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0991. Min Act: -0.0002

Data Index: 567892 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1095268 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0979. Min Act: -0.0001

Data Index: 318078 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0948. Min Act: -0.0001

Data Index: 263428 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1014. Min Act: -0.0001

Data Index: 51154 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1088. Min Act: -0.0001

Data Index: 438741 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1008. Min Act: -0.0002

Data Index: 349859 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1043. Min Act: -0.0001

Data Index: 86461 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1005189 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0943. Min Act: -0.0001

Data Index: 434444 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0931. Min Act: -0.0001

Data Index: 420464 (C4 (Web Text))

Max Activating Token Index: 509