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

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

Neuron 4964 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3407. Min Act: -0.0000

Data Index: 893660 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1047937 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1064366 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1656101 (Python Code)

Max Activating Token Index: 903

Text #4

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1310812 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1482320 (Python Code)

Max Activating Token Index: 472

Text #6

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2228. Min Act: -0.0000

Data Index: 253534 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2171. Min Act: -0.0000

Data Index: 171362 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1291291 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1911. Min Act: -0.0000

Data Index: 494564 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1404822 (Python Code)

Max Activating Token Index: 765

Text #11

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1368004 (Python Code)

Max Activating Token Index: 997

Text #12

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1564509 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1494286 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1856. Min Act: -0.0000

Data Index: 169726 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1391920 (Python Code)

Max Activating Token Index: 335

Text #16

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1534025 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1848. Min Act: -0.0000

Data Index: 123867 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1699. Min Act: -0.0000

Data Index: 35041 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1914. Min Act: -0.0000

Data Index: 886917 (C4 (Web Text))

Max Activating Token Index: 279