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

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

Neuron 3215 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1390557 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.4767. Min Act: -0.0000

Data Index: 1364987 (Python Code)

Max Activating Token Index: 732

Text #2

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1518250 (Python Code)

Max Activating Token Index: 877

Text #3

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1521189 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1420470 (Python Code)

Max Activating Token Index: 687

Text #5

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1409599 (Python Code)

Max Activating Token Index: 1004

Text #6

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1542141 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.1193. Min Act: -0.0001

Data Index: 1628119 (Python Code)

Max Activating Token Index: 436

Text #8

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.0797. Min Act: -0.0000

Data Index: 1482290 (Python Code)

Max Activating Token Index: 946

Text #9

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.0998. Min Act: -0.0000

Data Index: 1626602 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.1223. Min Act: -0.0001

Data Index: 1460060 (Python Code)

Max Activating Token Index: 685

Text #11

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.1260. Min Act: -0.0001

Data Index: 1484045 (Python Code)

Max Activating Token Index: 983

Text #12

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.0482. Min Act: -0.0001

Data Index: 1563876 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1491673 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1525185 (Python Code)

Max Activating Token Index: 461

Text #15

Max Range: 1.6290. Min Range: -1.6290

Max Act: 0.9986. Min Act: -0.0001

Data Index: 1497033 (Python Code)

Max Activating Token Index: 889

Text #16

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.0664. Min Act: -0.0000

Data Index: 857956 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 1.6290. Min Range: -1.6290

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1430917 (Python Code)

Max Activating Token Index: 364

Text #18

Max Range: 1.6290. Min Range: -1.6290

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1574498 (Python Code)

Max Activating Token Index: 223

Text #19

Max Range: 1.6290. Min Range: -1.6290

Max Act: 0.9754. Min Act: -0.0001

Data Index: 1507905 (Python Code)

Max Activating Token Index: 522