Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 226 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0002

Data Index: 768225 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0950. Min Act: -0.0002

Data Index: 960839 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0936. Min Act: -0.0002

Data Index: 787305 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0887. Min Act: -0.0002

Data Index: 207568 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0899. Min Act: -0.0002

Data Index: 22890 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0852. Min Act: -0.0002

Data Index: 578426 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1267488 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0868. Min Act: -0.0002

Data Index: 321380 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0839. Min Act: -0.0002

Data Index: 439616 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0817. Min Act: -0.0002

Data Index: 850498 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1080101 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1012376 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1089667 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0804. Min Act: -0.0002

Data Index: 542843 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1313402 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0807. Min Act: -0.0002

Data Index: 440950 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1127919 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1278185 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1038886 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0758. Min Act: -0.0002

Data Index: 60882 (C4 (Web Text))

Max Activating Token Index: 18