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

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

Neuron 2818 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.1002. Min Act: -0.0000

Data Index: 461779 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1306412 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0957. Min Act: -0.0000

Data Index: 756718 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0871. Min Act: -0.0000

Data Index: 246191 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0789. Min Act: -0.0000

Data Index: 936425 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0790. Min Act: -0.0000

Data Index: 906736 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1151043 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0769. Min Act: -0.0000

Data Index: 798544 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0735. Min Act: -0.0000

Data Index: 298859 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0729. Min Act: -0.0000

Data Index: 280274 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0760. Min Act: -0.0000

Data Index: 730310 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0727. Min Act: -0.0000

Data Index: 865350 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1154747 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0604. Min Act: -0.0000

Data Index: 835474 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1197481 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0715. Min Act: -0.0000

Data Index: 217661 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1108566 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0692. Min Act: -0.0000

Data Index: 321635 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0689. Min Act: -0.0000

Data Index: 696749 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0539. Min Act: -0.0000

Data Index: 989707 (C4 (Web Text))

Max Activating Token Index: 290