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

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

Neuron 3528 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: 0.4331. Min Range: -0.4331

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1158954 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3503. Min Act: -0.0000

Data Index: 484269 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2676. Min Act: -0.0000

Data Index: 845118 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2298. Min Act: -0.0000

Data Index: 116765 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2370. Min Act: -0.0000

Data Index: 327764 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2269. Min Act: -0.0000

Data Index: 418134 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1263551 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1196546 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2259. Min Act: -0.0000

Data Index: 410141 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2234. Min Act: -0.0000

Data Index: 435088 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2194. Min Act: -0.0000

Data Index: 808077 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2009. Min Act: -0.0000

Data Index: 640818 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2039. Min Act: -0.0000

Data Index: 297482 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.1982. Min Act: -0.0000

Data Index: 419406 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2124. Min Act: -0.0000

Data Index: 832681 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.1997. Min Act: -0.0000

Data Index: 885007 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2033. Min Act: -0.0000

Data Index: 270017 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.1948. Min Act: -0.0000

Data Index: 490778 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1253296 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1012588 (C4 (Web Text))

Max Activating Token Index: 670