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

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

Neuron 5274 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: 2.1291. Min Range: -2.1291

Max Act: 2.1291. Min Act: -0.0000

Data Index: 1437470 (Python Code)

Max Activating Token Index: 906

Text #1

Max Range: 2.1291. Min Range: -2.1291

Max Act: 1.4990. Min Act: -0.0000

Data Index: 1387672 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 2.1291. Min Range: -2.1291

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1621341 (Python Code)

Max Activating Token Index: 971

Text #3

Max Range: 2.1291. Min Range: -2.1291

Max Act: 1.4412. Min Act: -0.0000

Data Index: 1648168 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 2.1291. Min Range: -2.1291

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1606954 (Python Code)

Max Activating Token Index: 976

Text #5

Max Range: 2.1291. Min Range: -2.1291

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1446420 (Python Code)

Max Activating Token Index: 348

Text #6

Max Range: 2.1291. Min Range: -2.1291

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1515631 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 2.1291. Min Range: -2.1291

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1643007 (Python Code)

Max Activating Token Index: 929

Text #8

Max Range: 2.1291. Min Range: -2.1291

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1456072 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1489341 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1493713 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1483972 (Python Code)

Max Activating Token Index: 451

Text #12

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1628542 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1575807 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1571392 (Python Code)

Max Activating Token Index: 431

Text #15

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1529112 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1462010 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1562262 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1641514 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 2.1291. Min Range: -2.1291

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1474680 (Python Code)

Max Activating Token Index: 732