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

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

Neuron 5228 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3255. Min Range: -3.3255

Max Act: 3.3255. Min Act: -0.0000

Data Index: 1546480 (Python Code)

Max Activating Token Index: 363

Text #1

Max Range: 3.3255. Min Range: -3.3255

Max Act: 3.2293. Min Act: -0.0000

Data Index: 470538 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 3.3255. Min Range: -3.3255

Max Act: 3.0830. Min Act: -0.0000

Data Index: 84305 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 3.3255. Min Range: -3.3255

Max Act: 3.2096. Min Act: -0.0000

Data Index: 895395 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 3.3255. Min Range: -3.3255

Max Act: 3.0405. Min Act: -0.0000

Data Index: 86314 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.8868. Min Act: -0.0000

Data Index: 1130448 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 3.3255. Min Range: -3.3255

Max Act: 3.1775. Min Act: -0.0000

Data Index: 948802 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.9608. Min Act: -0.0000

Data Index: 1014150 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 3.3255. Min Range: -3.3255

Max Act: 3.0979. Min Act: -0.0000

Data Index: 1496221 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.9650. Min Act: -0.0000

Data Index: 202255 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.9254. Min Act: -0.0000

Data Index: 1094226 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.9215. Min Act: -0.0000

Data Index: 950363 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.8909. Min Act: -0.0000

Data Index: 657440 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.7599. Min Act: -0.0000

Data Index: 896567 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.7458. Min Act: -0.0000

Data Index: 966867 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.7712. Min Act: -0.0000

Data Index: 180581 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 3.3255. Min Range: -3.3255

Max Act: 3.0297. Min Act: -0.0000

Data Index: 930447 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.8686. Min Act: -0.0000

Data Index: 339331 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.7222. Min Act: -0.0000

Data Index: 1109753 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 3.3255. Min Range: -3.3255

Max Act: 2.8716. Min Act: -0.0000

Data Index: 516874 (C4 (Web Text))

Max Activating Token Index: 366