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

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

Neuron 4202 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.6538. Min Act: -0.0000

Data Index: 78021 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5942. Min Act: -0.0000

Data Index: 461796 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4928. Min Act: -0.0000

Data Index: 888354 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1024858 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5693. Min Act: -0.0000

Data Index: 123755 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5264. Min Act: -0.0000

Data Index: 26429 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5898. Min Act: -0.0000

Data Index: 344994 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1032647 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5378. Min Act: -0.0000

Data Index: 820859 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5037. Min Act: -0.0000

Data Index: 333105 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5601. Min Act: -0.0000

Data Index: 367272 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4379. Min Act: -0.0000

Data Index: 277356 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5283. Min Act: -0.0000

Data Index: 375711 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1230562 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4668. Min Act: -0.0000

Data Index: 949584 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.3852. Min Act: -0.0000

Data Index: 96199 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4346. Min Act: -0.0000

Data Index: 310426 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4733. Min Act: -0.0000

Data Index: 844717 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4380. Min Act: -0.0000

Data Index: 335359 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1203422 (C4 (Web Text))

Max Activating Token Index: 466