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

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

Neuron 229 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.6297. Min Act: -0.0003

Data Index: 94291 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.6296. Min Act: -0.0003

Data Index: 548846 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5993. Min Act: -0.0003

Data Index: 931389 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.6056. Min Act: -0.0002

Data Index: 1119444 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5843. Min Act: -0.0003

Data Index: 573666 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5781. Min Act: -0.0002

Data Index: 954126 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5852. Min Act: -0.0002

Data Index: 862018 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5575. Min Act: -0.0003

Data Index: 292003 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5717. Min Act: -0.0002

Data Index: 777635 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5557. Min Act: -0.0003

Data Index: 1147350 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5519. Min Act: -0.0003

Data Index: 812337 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5312. Min Act: -0.0002

Data Index: 697741 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5653. Min Act: -0.0003

Data Index: 1238841 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5599. Min Act: -0.0002

Data Index: 233385 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5413. Min Act: -0.0003

Data Index: 1160848 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5220. Min Act: -0.0003

Data Index: 1214488 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5379. Min Act: -0.0003

Data Index: 496599 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5371. Min Act: -0.0003

Data Index: 1283173 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5367. Min Act: -0.0003

Data Index: 1037052 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.6297. Min Range: -0.6297

Max Act: 0.5353. Min Act: -0.0003

Data Index: 1183833 (C4 (Web Text))

Max Activating Token Index: 378