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

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

Neuron 930 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1549119 (Python Code)

Max Activating Token Index: 822

Text #1

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1644793 (Python Code)

Max Activating Token Index: 796

Text #2

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1498750 (Python Code)

Max Activating Token Index: 616

Text #3

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1412099 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1452283 (Python Code)

Max Activating Token Index: 637

Text #5

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1268. Min Act: -0.0000

Data Index: 914211 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1380516 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1387340 (Python Code)

Max Activating Token Index: 518

Text #8

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1638243 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1050. Min Act: -0.0000

Data Index: 12812 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1435441 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1057. Min Act: -0.0000

Data Index: 477838 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1015. Min Act: -0.0000

Data Index: 129091 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1585107 (Python Code)

Max Activating Token Index: 831

Text #14

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1539169 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.0803. Min Act: -0.0000

Data Index: 646753 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1051. Min Act: -0.0000

Data Index: 119863 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1554628 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1402664 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1533847 (Python Code)

Max Activating Token Index: 645