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

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

Neuron 2073 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0002

Data Index: 709597 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1300300 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0100. Min Act: -0.0002

Data Index: 689908 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1124862 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0002

Data Index: 300835 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0097. Min Act: -0.0002

Data Index: 966708 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0002

Data Index: 546038 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1237361 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0098. Min Act: -0.0002

Data Index: 582726 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0098. Min Act: -0.0002

Data Index: 780425 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0095. Min Act: -0.0002

Data Index: 463668 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1175013 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1032634 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0097. Min Act: -0.0002

Data Index: 286083 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0097. Min Act: -0.0002

Data Index: 702121 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0097. Min Act: -0.0002

Data Index: 362896 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0097. Min Act: -0.0002

Data Index: 334285 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1318797 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1228410 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0096. Min Act: -0.0002

Data Index: 101751 (C4 (Web Text))

Max Activating Token Index: 320