Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1987 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1282. Min Act: -0.0003

Data Index: 252464 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1167. Min Act: -0.0003

Data Index: 1200597 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1185. Min Act: -0.0003

Data Index: 88254 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1120. Min Act: -0.0003

Data Index: 296811 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1062. Min Act: -0.0003

Data Index: 1069177 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1099. Min Act: -0.0003

Data Index: 304562 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1109. Min Act: -0.0004

Data Index: 916867 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1098. Min Act: -0.0003

Data Index: 374972 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1052. Min Act: -0.0003

Data Index: 515682 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1008. Min Act: -0.0003

Data Index: 794120 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1047. Min Act: -0.0003

Data Index: 327929 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1066. Min Act: -0.0003

Data Index: 630000 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1009. Min Act: -0.0004

Data Index: 68459 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1055. Min Act: -0.0003

Data Index: 211832 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.0957. Min Act: -0.0004

Data Index: 868617 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1030. Min Act: -0.0003

Data Index: 503137 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1012. Min Act: -0.0004

Data Index: 120642 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1045. Min Act: -0.0004

Data Index: 1007300 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1016. Min Act: -0.0003

Data Index: 303706 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.1282. Min Range: -0.1282

Max Act: 0.1059. Min Act: -0.0004

Data Index: 1106551 (C4 (Web Text))

Max Activating Token Index: 534