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

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

Neuron 667 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1324985 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1048. Min Act: -0.0000

Data Index: 667620 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0963. Min Act: -0.0000

Data Index: 986428 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0882. Min Act: -0.0000

Data Index: 185833 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0892. Min Act: -0.0000

Data Index: 407640 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1098146 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0858. Min Act: -0.0000

Data Index: 334431 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0832. Min Act: -0.0000

Data Index: 316270 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0795. Min Act: -0.0000

Data Index: 836054 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1162795 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0816. Min Act: -0.0000

Data Index: 350773 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0794. Min Act: -0.0000

Data Index: 662574 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0744. Min Act: -0.0000

Data Index: 799451 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1529157 (Python Code)

Max Activating Token Index: 730

Text #14

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0744. Min Act: -0.0000

Data Index: 404027 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0748. Min Act: -0.0000

Data Index: 1365088 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0697. Min Act: -0.0000

Data Index: 623059 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1396469 (Python Code)

Max Activating Token Index: 540

Text #18

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0743. Min Act: -0.0000

Data Index: 937085 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1291495 (C4 (Web Text))

Max Activating Token Index: 588