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

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

Neuron 3015 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: 0.1015. Min Range: -0.1015

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1261931 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1121779 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1109552 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0891. Min Act: -0.0001

Data Index: 783070 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0872. Min Act: -0.0001

Data Index: 444152 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0891. Min Act: -0.0001

Data Index: 978416 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0857. Min Act: -0.0001

Data Index: 147675 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0847. Min Act: -0.0001

Data Index: 374046 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0830. Min Act: -0.0001

Data Index: 391778 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0830. Min Act: -0.0001

Data Index: 112692 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0804. Min Act: -0.0001

Data Index: 792473 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0767. Min Act: -0.0001

Data Index: 55738 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1246648 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0775. Min Act: -0.0001

Data Index: 197842 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0822. Min Act: -0.0001

Data Index: 939683 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1339483 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0753. Min Act: -0.0001

Data Index: 734654 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0749. Min Act: -0.0001

Data Index: 263103 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0809. Min Act: -0.0001

Data Index: 862298 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1133596 (C4 (Web Text))

Max Activating Token Index: 590