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

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

Neuron 2556 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2189. Min Act: -0.0002

Data Index: 1157128 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2104. Min Act: -0.0002

Data Index: 829461 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2095. Min Act: -0.0002

Data Index: 270876 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2194. Min Act: -0.0002

Data Index: 1193082 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1990. Min Act: -0.0002

Data Index: 214601 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1918. Min Act: -0.0002

Data Index: 338222 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2184. Min Act: -0.0002

Data Index: 931172 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2057. Min Act: -0.0002

Data Index: 198067 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1957. Min Act: -0.0002

Data Index: 395154 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1850. Min Act: -0.0002

Data Index: 254654 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2098. Min Act: -0.0002

Data Index: 792851 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2048. Min Act: -0.0002

Data Index: 905017 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.1933. Min Act: -0.0002

Data Index: 187235 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2069. Min Act: -0.0002

Data Index: 128922 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2007. Min Act: -0.0002

Data Index: 745429 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2049. Min Act: -0.0002

Data Index: 641006 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2005. Min Act: -0.0002

Data Index: 289674 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2191. Min Act: -0.0002

Data Index: 97500 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2153. Min Act: -0.0002

Data Index: 545176 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.2194. Min Range: -0.2194

Max Act: 0.2117. Min Act: -0.0002

Data Index: 314799 (C4 (Web Text))

Max Activating Token Index: 302