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

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

Neuron 161 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: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1288600 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0783. Min Act: -0.0002

Data Index: 369772 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0775. Min Act: -0.0002

Data Index: 923799 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1063058 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0794. Min Act: -0.0002

Data Index: 124693 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0789. Min Act: -0.0002

Data Index: 112149 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1615231 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0747. Min Act: -0.0002

Data Index: 389312 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0726. Min Act: -0.0002

Data Index: 387189 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1378629 (Python Code)

Max Activating Token Index: 302

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0713. Min Act: -0.0002

Data Index: 810441 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1198391 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1083970 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1560762 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0730. Min Act: -0.0002

Data Index: 897959 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0726. Min Act: -0.0002

Data Index: 119299 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1008733 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1557964 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1486217 (Python Code)

Max Activating Token Index: 36

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0696. Min Act: -0.0002

Data Index: 626423 (C4 (Web Text))

Max Activating Token Index: 181