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

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

Neuron 2712 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1120684 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1309431 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2098. Min Act: -0.0000

Data Index: 957149 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2083. Min Act: -0.0000

Data Index: 884650 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1902. Min Act: -0.0000

Data Index: 15945 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1939. Min Act: -0.0000

Data Index: 80439 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1017694 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1290639 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1342436 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1053741 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1162976 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1805. Min Act: -0.0000

Data Index: 647571 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1804. Min Act: -0.0000

Data Index: 823027 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1801. Min Act: -0.0000

Data Index: 11581 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1720. Min Act: -0.0000

Data Index: 621948 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1750. Min Act: -0.0000

Data Index: 424601 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1745. Min Act: -0.0001

Data Index: 962122 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1676. Min Act: -0.0000

Data Index: 192666 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1664. Min Act: -0.0000

Data Index: 757230 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1068159 (C4 (Web Text))

Max Activating Token Index: 328