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

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

Neuron 4091 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7495. Min Range: -3.7495

Max Act: 3.7495. Min Act: -0.0002

Data Index: 1223126 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.4033. Min Act: -0.0001

Data Index: 2590 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 3.7495. Min Range: -3.7495

Max Act: 2.1744. Min Act: -0.0001

Data Index: 205735 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.9996. Min Act: -0.0001

Data Index: 596473 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.7843. Min Act: -0.0001

Data Index: 610985 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.8998. Min Act: -0.0001

Data Index: 138278 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.9191. Min Act: -0.0001

Data Index: 518273 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.8005. Min Act: -0.0001

Data Index: 479039 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.8332. Min Act: -0.0001

Data Index: 305146 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.7348. Min Act: -0.0002

Data Index: 689267 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.8878. Min Act: -0.0001

Data Index: 83158 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.8343. Min Act: -0.0001

Data Index: 145654 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.7403. Min Act: -0.0001

Data Index: 1051717 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.8437. Min Act: -0.0001

Data Index: 534846 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.7304. Min Act: -0.0001

Data Index: 30851 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.9246. Min Act: -0.0001

Data Index: 1229008 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.7846. Min Act: -0.0002

Data Index: 312590 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.7685. Min Act: -0.0001

Data Index: 440956 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.6084. Min Act: -0.0001

Data Index: 1090853 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 3.7495. Min Range: -3.7495

Max Act: 1.6871. Min Act: -0.0001

Data Index: 703194 (C4 (Web Text))

Max Activating Token Index: 541