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

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

Neuron 4924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.1442. Min Act: -0.0000

Data Index: 1509566 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 3.2494. Min Range: -3.2494

Max Act: 3.2494. Min Act: -0.0000

Data Index: 1546042 (Python Code)

Max Activating Token Index: 949

Text #2

Max Range: 3.2494. Min Range: -3.2494

Max Act: 2.9767. Min Act: -0.0000

Data Index: 1364132 (Python Code)

Max Activating Token Index: 139

Text #3

Max Range: 3.2494. Min Range: -3.2494

Max Act: 2.5958. Min Act: -0.0000

Data Index: 1366756 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 3.2494. Min Range: -3.2494

Max Act: 2.5391. Min Act: -0.0000

Data Index: 1567663 (Python Code)

Max Activating Token Index: 34

Text #5

Max Range: 3.2494. Min Range: -3.2494

Max Act: 2.0510. Min Act: -0.0000

Data Index: 735627 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.9236. Min Act: -0.0000

Data Index: 811902 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.8595. Min Act: -0.0000

Data Index: 656538 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.8267. Min Act: -0.0000

Data Index: 827173 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.8264. Min Act: -0.0000

Data Index: 194640 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1215833 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.6937. Min Act: -0.0000

Data Index: 184669 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.7883. Min Act: -0.0000

Data Index: 1165560 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.7931. Min Act: -0.0000

Data Index: 270274 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.9759. Min Act: -0.0000

Data Index: 713259 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.7378. Min Act: -0.0000

Data Index: 299078 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1016057 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.7259. Min Act: -0.0000

Data Index: 369264 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.7262. Min Act: -0.0000

Data Index: 1134903 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 3.2494. Min Range: -3.2494

Max Act: 1.7152. Min Act: -0.0000

Data Index: 251011 (C4 (Web Text))

Max Activating Token Index: 474