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

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

Neuron 5520 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: 0.1367. Min Range: -0.1367

Max Act: 0.1367. Min Act: -0.0000

Data Index: 886059 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1058. Min Act: -0.0000

Data Index: 258167 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1338723 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1221. Min Act: -0.0000

Data Index: 275454 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1022. Min Act: -0.0000

Data Index: 668274 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1029. Min Act: -0.0000

Data Index: 691176 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1005217 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1015. Min Act: -0.0000

Data Index: 243237 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0798. Min Act: -0.0000

Data Index: 880216 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0845. Min Act: -0.0000

Data Index: 501772 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0746. Min Act: -0.0000

Data Index: 466869 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1656206 (Python Code)

Max Activating Token Index: 403

Text #12

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0811. Min Act: -0.0000

Data Index: 612294 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1175763 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0804. Min Act: -0.0000

Data Index: 152828 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0816. Min Act: -0.0000

Data Index: 187465 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0773. Min Act: -0.0000

Data Index: 708725 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0782. Min Act: -0.0000

Data Index: 454273 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0931. Min Act: -0.0000

Data Index: 522800 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0804. Min Act: -0.0000

Data Index: 886821 (C4 (Web Text))

Max Activating Token Index: 334