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

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

Neuron 1162 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.7119. Min Act: -0.0002

Data Index: 176381 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.6908. Min Act: -0.0002

Data Index: 692093 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.6481. Min Act: -0.0002

Data Index: 659834 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.6280. Min Act: -0.0002

Data Index: 269 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.6140. Min Act: -0.0002

Data Index: 296463 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5393. Min Act: -0.0002

Data Index: 270793 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5960. Min Act: -0.0002

Data Index: 463666 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5564. Min Act: -0.0002

Data Index: 962353 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5592. Min Act: -0.0002

Data Index: 265391 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5622. Min Act: -0.0002

Data Index: 1216141 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5877. Min Act: -0.0002

Data Index: 269159 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5317. Min Act: -0.0002

Data Index: 363139 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5225. Min Act: -0.0002

Data Index: 600476 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5308. Min Act: -0.0002

Data Index: 1001812 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5284. Min Act: -0.0002

Data Index: 123965 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5325. Min Act: -0.0002

Data Index: 1172919 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5331. Min Act: -0.0002

Data Index: 583473 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5620. Min Act: -0.0002

Data Index: 882781 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5039. Min Act: -0.0002

Data Index: 115694 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4737. Min Act: -0.0002

Data Index: 724985 (C4 (Web Text))

Max Activating Token Index: 454