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

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

Neuron 5921 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: 2.9598. Min Range: -2.9598

Max Act: 2.9598. Min Act: -0.0000

Data Index: 1643519 (Python Code)

Max Activating Token Index: 193

Text #1

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.7732. Min Act: -0.0000

Data Index: 1444766 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.8137. Min Act: -0.0000

Data Index: 1550292 (Python Code)

Max Activating Token Index: 611

Text #3

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.6376. Min Act: -0.0000

Data Index: 1547339 (Python Code)

Max Activating Token Index: 290

Text #4

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.5605. Min Act: -0.0000

Data Index: 1655442 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.3491. Min Act: -0.0000

Data Index: 1539122 (Python Code)

Max Activating Token Index: 640

Text #6

Max Range: 2.9598. Min Range: -2.9598

Max Act: 1.8971. Min Act: -0.0000

Data Index: 1557510 (Python Code)

Max Activating Token Index: 872

Text #7

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.3381. Min Act: -0.0000

Data Index: 1501706 (Python Code)

Max Activating Token Index: 241

Text #8

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.5097. Min Act: -0.0000

Data Index: 1452310 (Python Code)

Max Activating Token Index: 681

Text #9

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.3609. Min Act: -0.0000

Data Index: 1537059 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.4812. Min Act: -0.0000

Data Index: 1423538 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.0719. Min Act: -0.0000

Data Index: 1432492 (Python Code)

Max Activating Token Index: 807

Text #12

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.2943. Min Act: -0.0000

Data Index: 1465220 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.2887. Min Act: -0.0000

Data Index: 1385015 (Python Code)

Max Activating Token Index: 537

Text #14

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.1669. Min Act: -0.0000

Data Index: 1453724 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.1637. Min Act: -0.0000

Data Index: 1601052 (Python Code)

Max Activating Token Index: 892

Text #16

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.2350. Min Act: -0.0000

Data Index: 1588453 (Python Code)

Max Activating Token Index: 151

Text #17

Max Range: 2.9598. Min Range: -2.9598

Max Act: 2.2507. Min Act: -0.0000

Data Index: 1639919 (Python Code)

Max Activating Token Index: 934

Text #18

Max Range: 2.9598. Min Range: -2.9598

Max Act: 1.9862. Min Act: -0.0000

Data Index: 1523086 (Python Code)

Max Activating Token Index: 102

Text #19

Max Range: 2.9598. Min Range: -2.9598

Max Act: 1.8717. Min Act: -0.0000

Data Index: 1483830 (Python Code)

Max Activating Token Index: 47