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

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

Neuron 12 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1868. Min Range: -1.1868

Max Act: 1.1868. Min Act: -0.0000

Data Index: 1646074 (Python Code)

Max Activating Token Index: 441

Text #1

Max Range: 1.1868. Min Range: -1.1868

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1604848 (Python Code)

Max Activating Token Index: 650

Text #2

Max Range: 1.1868. Min Range: -1.1868

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1562420 (Python Code)

Max Activating Token Index: 396

Text #3

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1597451 (Python Code)

Max Activating Token Index: 936

Text #4

Max Range: 1.1868. Min Range: -1.1868

Max Act: 1.0022. Min Act: -0.0000

Data Index: 1563252 (Python Code)

Max Activating Token Index: 724

Text #5

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1617554 (Python Code)

Max Activating Token Index: 366

Text #6

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1394885 (Python Code)

Max Activating Token Index: 213

Text #7

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1518157 (Python Code)

Max Activating Token Index: 782

Text #8

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1522534 (Python Code)

Max Activating Token Index: 940

Text #9

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1394557 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1389422 (Python Code)

Max Activating Token Index: 532

Text #11

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1552328 (Python Code)

Max Activating Token Index: 421

Text #12

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1400828 (Python Code)

Max Activating Token Index: 874

Text #13

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1517728 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1489437 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1410532 (Python Code)

Max Activating Token Index: 702

Text #16

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1639324 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1588091 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1391103 (Python Code)

Max Activating Token Index: 473

Text #19

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1600027 (Python Code)

Max Activating Token Index: 201