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

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

Neuron 3884 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: 0.0087. Min Range: -0.0087

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1448647 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1488211 (Python Code)

Max Activating Token Index: 617

Text #2

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1444664 (Python Code)

Max Activating Token Index: 386

Text #3

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1434328 (Python Code)

Max Activating Token Index: 914

Text #4

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0068. Min Act: -0.0003

Data Index: 283261 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0057. Min Act: -0.0003

Data Index: 951729 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0059. Min Act: -0.0002

Data Index: 225594 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0064. Min Act: -0.0003

Data Index: 296296 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1432931 (Python Code)

Max Activating Token Index: 370

Text #9

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0064. Min Act: -0.0002

Data Index: 25711 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1041107 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1350901 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0069. Min Act: -0.0003

Data Index: 268234 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1077612 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0063. Min Act: -0.0003

Data Index: 410043 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1029047 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0049. Min Act: -0.0003

Data Index: 474277 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1205030 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1406196 (Python Code)

Max Activating Token Index: 383

Text #19

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0064. Min Act: -0.0002

Data Index: 225636 (C4 (Web Text))

Max Activating Token Index: 767