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

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

Neuron 3785 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: 0.0918. Min Range: -0.0918

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1202283 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1241275 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1548895 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1400497 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1482247 (Python Code)

Max Activating Token Index: 820

Text #5

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0829. Min Act: -0.0002

Data Index: 241112 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1617945 (Python Code)

Max Activating Token Index: 697

Text #7

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1514292 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1602267 (Python Code)

Max Activating Token Index: 367

Text #9

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1400029 (Python Code)

Max Activating Token Index: 985

Text #10

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1603850 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1524202 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1623763 (Python Code)

Max Activating Token Index: 826

Text #13

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0686. Min Act: -0.0002

Data Index: 758955 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1650940 (Python Code)

Max Activating Token Index: 841

Text #15

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1570560 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0705. Min Act: -0.0002

Data Index: 568982 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0728. Min Act: -0.0002

Data Index: 162904 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1240432 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1181469 (C4 (Web Text))

Max Activating Token Index: 704