Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2765 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1095184 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9853. Min Act: 0.0000

Data Index: 1324893 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9992. Min Act: 0.0000

Data Index: 1131830 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0097. Min Act: -0.0000

Data Index: 583915 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0319. Min Act: -0.0000

Data Index: 643156 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9986. Min Act: -0.0000

Data Index: 560868 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0035. Min Act: -0.0000

Data Index: 998997 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9959. Min Act: -0.0000

Data Index: 588260 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1024664 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0216. Min Act: -0.0000

Data Index: 817810 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9417. Min Act: -0.0000

Data Index: 67501 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9290. Min Act: 0.0000

Data Index: 581828 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9543. Min Act: -0.0000

Data Index: 569422 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9239. Min Act: 0.0000

Data Index: 71884 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9130. Min Act: -0.0000

Data Index: 639956 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9142. Min Act: 0.0000

Data Index: 524220 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8859. Min Act: -0.0000

Data Index: 880118 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.9231. Min Act: -0.0000

Data Index: 411791 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1051314 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.1666. Min Range: -1.1666

Max Act: 0.8828. Min Act: -0.0000

Data Index: 82252 (C4 (Web Text))

Max Activating Token Index: 697