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

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

Neuron 1248 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1074. Min Act: -0.0000

Data Index: 217132 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0877. Min Act: -0.0000

Data Index: 741309 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0802. Min Act: -0.0000

Data Index: 286272 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0822. Min Act: -0.0000

Data Index: 845690 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0673. Min Act: -0.0000

Data Index: 195186 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1148002 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0622. Min Act: -0.0000

Data Index: 230451 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1097877 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0619. Min Act: -0.0000

Data Index: 864524 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0634. Min Act: -0.0000

Data Index: 999911 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0576. Min Act: -0.0000

Data Index: 47530 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1258254 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1227977 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1264550 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0589. Min Act: -0.0000

Data Index: 865041 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0571. Min Act: -0.0000

Data Index: 892330 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0570. Min Act: -0.0000

Data Index: 984722 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0557. Min Act: -0.0000

Data Index: 911682 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1180410 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1092732 (C4 (Web Text))

Max Activating Token Index: 1013