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

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

Neuron 3966 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.7573. Min Act: -0.0001

Data Index: 1603009 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6836. Min Act: -0.0001

Data Index: 1643141 (Python Code)

Max Activating Token Index: 116

Text #2

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1509619 (Python Code)

Max Activating Token Index: 862

Text #3

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.7174. Min Act: -0.0001

Data Index: 1636299 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6519. Min Act: -0.0001

Data Index: 1384044 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1483337 (Python Code)

Max Activating Token Index: 721

Text #6

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6436. Min Act: -0.0001

Data Index: 1572238 (Python Code)

Max Activating Token Index: 715

Text #7

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6614. Min Act: -0.0001

Data Index: 1576439 (Python Code)

Max Activating Token Index: 280

Text #8

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1598433 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5946. Min Act: -0.0001

Data Index: 1449804 (Python Code)

Max Activating Token Index: 810

Text #10

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1488025 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1420901 (Python Code)

Max Activating Token Index: 643

Text #12

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6881. Min Act: -0.0001

Data Index: 1600393 (Python Code)

Max Activating Token Index: 895

Text #13

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5946. Min Act: -0.0001

Data Index: 1481666 (Python Code)

Max Activating Token Index: 374

Text #14

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6084. Min Act: -0.0001

Data Index: 1621888 (Python Code)

Max Activating Token Index: 786

Text #15

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6336. Min Act: -0.0001

Data Index: 1414400 (Python Code)

Max Activating Token Index: 985

Text #16

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6577. Min Act: -0.0001

Data Index: 1518266 (Python Code)

Max Activating Token Index: 885

Text #17

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6436. Min Act: -0.0001

Data Index: 1517221 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6263. Min Act: -0.0001

Data Index: 1634421 (Python Code)

Max Activating Token Index: 993

Text #19

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6224. Min Act: -0.0001

Data Index: 1588260 (Python Code)

Max Activating Token Index: 837