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

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

Neuron 4000 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1617. Min Range: -3.1617

Max Act: 3.1617. Min Act: -0.0001

Data Index: 1654501 (Python Code)

Max Activating Token Index: 929

Text #1

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.7398. Min Act: -0.0001

Data Index: 1544463 (Python Code)

Max Activating Token Index: 956

Text #2

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.3263. Min Act: -0.0001

Data Index: 1518078 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 3.1617. Min Range: -3.1617

Max Act: 2.1558. Min Act: -0.0001

Data Index: 1434910 (Python Code)

Max Activating Token Index: 869

Text #4

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.5698. Min Act: -0.0001

Data Index: 1643420 (Python Code)

Max Activating Token Index: 891

Text #5

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.6815. Min Act: -0.0001

Data Index: 1635673 (Python Code)

Max Activating Token Index: 929

Text #6

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.3792. Min Act: -0.0001

Data Index: 1452880 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.3795. Min Act: -0.0001

Data Index: 1586925 (Python Code)

Max Activating Token Index: 929

Text #8

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.2416. Min Act: -0.0001

Data Index: 1622783 (Python Code)

Max Activating Token Index: 559

Text #9

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.1908. Min Act: -0.0001

Data Index: 1487634 (Python Code)

Max Activating Token Index: 859

Text #10

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.1954. Min Act: -0.0001

Data Index: 1631302 (Python Code)

Max Activating Token Index: 978

Text #11

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.2877. Min Act: -0.0001

Data Index: 1373268 (Python Code)

Max Activating Token Index: 601

Text #12

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1550880 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.2284. Min Act: -0.0001

Data Index: 1647623 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1615135 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.1164. Min Act: -0.0001

Data Index: 1642549 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.1472. Min Act: -0.0001

Data Index: 1598236 (Python Code)

Max Activating Token Index: 531

Text #17

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.1275. Min Act: -0.0000

Data Index: 1438829 (Python Code)

Max Activating Token Index: 864

Text #18

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.1629. Min Act: -0.0001

Data Index: 1436593 (Python Code)

Max Activating Token Index: 770

Text #19

Max Range: 3.1617. Min Range: -3.1617

Max Act: 1.1515. Min Act: -0.0001

Data Index: 1368259 (Python Code)

Max Activating Token Index: 79