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

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

Neuron 1796 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1045. Min Act: -0.0005

Data Index: 715371 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1014. Min Act: -0.0005

Data Index: 239910 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0925. Min Act: -0.0005

Data Index: 37453 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0911. Min Act: -0.0005

Data Index: 1128264 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0898. Min Act: -0.0005

Data Index: 151139 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0829. Min Act: -0.0005

Data Index: 813368 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0843. Min Act: -0.0005

Data Index: 80485 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0838. Min Act: -0.0005

Data Index: 15537 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0836. Min Act: -0.0005

Data Index: 732064 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0833. Min Act: -0.0005

Data Index: 78907 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0815. Min Act: -0.0005

Data Index: 758644 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0782. Min Act: -0.0005

Data Index: 517626 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0822. Min Act: -0.0005

Data Index: 1220868 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0772. Min Act: -0.0005

Data Index: 321530 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0784. Min Act: -0.0005

Data Index: 1173287 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0738. Min Act: -0.0005

Data Index: 753557 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0720. Min Act: -0.0005

Data Index: 1015029 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0757. Min Act: -0.0005

Data Index: 160965 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0743. Min Act: -0.0005

Data Index: 550207 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0748. Min Act: -0.0005

Data Index: 756301 (C4 (Web Text))

Max Activating Token Index: 266