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

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

Neuron 4539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.5592. Min Act: -0.0000

Data Index: 56262 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.4032. Min Act: -0.0000

Data Index: 1208986 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.3977. Min Act: -0.0000

Data Index: 516869 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.2998. Min Act: -0.0000

Data Index: 546270 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.3101. Min Act: -0.0000

Data Index: 506377 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.2286. Min Act: -0.0000

Data Index: 600389 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.2132. Min Act: -0.0000

Data Index: 422317 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1354907 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.1667. Min Act: -0.0000

Data Index: 337379 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.1507. Min Act: -0.0000

Data Index: 658364 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1061524 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.0830. Min Act: -0.0000

Data Index: 103103 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.1081. Min Act: -0.0000

Data Index: 509913 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.0639. Min Act: -0.0000

Data Index: 871626 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.1271. Min Act: -0.0000

Data Index: 437533 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.0900. Min Act: -0.0000

Data Index: 992931 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.1137. Min Act: -0.0000

Data Index: 110918 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.0355. Min Act: -0.0000

Data Index: 569320 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.0660. Min Act: -0.0000

Data Index: 887453 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.5592. Min Range: -1.5592

Max Act: 1.0985. Min Act: -0.0000

Data Index: 411707 (C4 (Web Text))

Max Activating Token Index: 33