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

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

Neuron 92 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1487160 (Python Code)

Max Activating Token Index: 308

Text #1

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1577647 (Python Code)

Max Activating Token Index: 320

Text #2

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1522080 (Python Code)

Max Activating Token Index: 651

Text #3

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1579136 (Python Code)

Max Activating Token Index: 955

Text #4

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1568996 (Python Code)

Max Activating Token Index: 969

Text #5

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0413. Min Act: -0.0000

Data Index: 1640461 (Python Code)

Max Activating Token Index: 296

Text #6

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0023. Min Act: -0.0000

Data Index: 1627079 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1551271 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1452449 (Python Code)

Max Activating Token Index: 463

Text #9

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1412272 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1592889 (Python Code)

Max Activating Token Index: 388

Text #11

Max Range: 1.0413. Min Range: -1.0413

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1650566 (Python Code)

Max Activating Token Index: 435

Text #12

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1539062 (Python Code)

Max Activating Token Index: 273

Text #13

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1627888 (Python Code)

Max Activating Token Index: 782

Text #14

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1533035 (Python Code)

Max Activating Token Index: 99

Text #15

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8903. Min Act: -0.0000

Data Index: 1528958 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1365873 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1398242 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1502586 (Python Code)

Max Activating Token Index: 703

Text #19

Max Range: 1.0413. Min Range: -1.0413

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1460230 (Python Code)

Max Activating Token Index: 151