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

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

Neuron 2702 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: 0.0869. Min Range: -0.0869

Max Act: 0.0848. Min Act: -0.0002

Data Index: 312101 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0856. Min Act: -0.0002

Data Index: 376134 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0834. Min Act: -0.0002

Data Index: 284257 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0869. Min Act: -0.0002

Data Index: 839559 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0826. Min Act: -0.0002

Data Index: 430080 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0836. Min Act: -0.0002

Data Index: 714930 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0763. Min Act: -0.0002

Data Index: 244008 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0761. Min Act: -0.0002

Data Index: 343230 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1211951 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0767. Min Act: -0.0002

Data Index: 120466 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0775. Min Act: -0.0002

Data Index: 614036 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0776. Min Act: -0.0002

Data Index: 88213 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1290366 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1352981 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0777. Min Act: -0.0002

Data Index: 679074 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0796. Min Act: -0.0002

Data Index: 648694 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0756. Min Act: -0.0002

Data Index: 56666 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0751. Min Act: -0.0002

Data Index: 960266 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1283405 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1162234 (C4 (Web Text))

Max Activating Token Index: 785