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

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

Neuron 2982 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1243828 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1874. Min Act: -0.0000

Data Index: 950162 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1029216 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1498. Min Act: -0.0000

Data Index: 39094 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1534. Min Act: -0.0000

Data Index: 777794 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1466. Min Act: -0.0000

Data Index: 14300 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1405. Min Act: -0.0000

Data Index: 12252 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1534895 (Python Code)

Max Activating Token Index: 182

Text #8

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1389958 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1232. Min Act: -0.0001

Data Index: 630205 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1477. Min Act: -0.0000

Data Index: 117769 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1415. Min Act: -0.0000

Data Index: 390886 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1360. Min Act: -0.0000

Data Index: 82835 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1301. Min Act: -0.0000

Data Index: 1295456 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1432. Min Act: -0.0000

Data Index: 888896 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1432313 (Python Code)

Max Activating Token Index: 129

Text #16

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1301481 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1432185 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1308. Min Act: -0.0000

Data Index: 58236 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1035437 (C4 (Web Text))

Max Activating Token Index: 1013