Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3527 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.7795. Min Act: -0.0001

Data Index: 586976 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.4910. Min Act: -0.0001

Data Index: 250872 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2545. Min Act: -0.0001

Data Index: 1124713 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2843. Min Act: -0.0001

Data Index: 1259019 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 1.7795. Min Range: -1.7795

Max Act: 0.9817. Min Act: -0.0001

Data Index: 234859 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.1564. Min Act: -0.0001

Data Index: 59376 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.1871. Min Act: -0.0001

Data Index: 1222473 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.1734. Min Act: -0.0001

Data Index: 188636 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2022. Min Act: -0.0001

Data Index: 757688 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.0928. Min Act: -0.0001

Data Index: 1212987 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2109. Min Act: -0.0001

Data Index: 1242036 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.1533. Min Act: -0.0001

Data Index: 376763 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.1827. Min Act: -0.0001

Data Index: 699839 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.1911. Min Act: -0.0001

Data Index: 283772 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.0867. Min Act: -0.0001

Data Index: 1075463 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.0679. Min Act: -0.0001

Data Index: 3772 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.0385. Min Act: -0.0001

Data Index: 444022 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2741. Min Act: -0.0001

Data Index: 522043 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.1170. Min Act: -0.0001

Data Index: 965637 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.0142. Min Act: -0.0001

Data Index: 875959 (C4 (Web Text))

Max Activating Token Index: 417