Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 816 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1200. Min Act: -0.0002

Data Index: 489550 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0970. Min Act: -0.0002

Data Index: 371358 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0963. Min Act: -0.0001

Data Index: 107415 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0904. Min Act: -0.0002

Data Index: 906341 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0820. Min Act: -0.0002

Data Index: 275777 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0890. Min Act: -0.0002

Data Index: 372506 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1192946 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0883. Min Act: -0.0002

Data Index: 314491 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0888. Min Act: -0.0002

Data Index: 230015 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0866. Min Act: -0.0002

Data Index: 927728 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0868. Min Act: -0.0002

Data Index: 972922 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1168392 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0844. Min Act: -0.0002

Data Index: 282588 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0837. Min Act: -0.0002

Data Index: 599452 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1257954 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0815. Min Act: -0.0002

Data Index: 942117 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0791. Min Act: -0.0002

Data Index: 458920 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0801. Min Act: -0.0002

Data Index: 948295 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0766. Min Act: -0.0002

Data Index: 518052 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0768. Min Act: -0.0002

Data Index: 591990 (C4 (Web Text))

Max Activating Token Index: 827