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

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

Neuron 1246 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1455413 (Python Code)

Max Activating Token Index: 603

Text #1

Max Range: 1.3083. Min Range: -1.3083

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1502366 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1482584 (Python Code)

Max Activating Token Index: 78

Text #3

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1368619 (Python Code)

Max Activating Token Index: 810

Text #4

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1499772 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1656446 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1378901 (Python Code)

Max Activating Token Index: 665

Text #7

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1528298 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1396605 (Python Code)

Max Activating Token Index: 263

Text #9

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1565034 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1439555 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1649660 (Python Code)

Max Activating Token Index: 833

Text #12

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8467. Min Act: 0.0000

Data Index: 1508829 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1560407 (Python Code)

Max Activating Token Index: 710

Text #14

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1497713 (Python Code)

Max Activating Token Index: 325

Text #15

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1402939 (Python Code)

Max Activating Token Index: 168

Text #16

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1540574 (Python Code)

Max Activating Token Index: 331

Text #17

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1481210 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1470464 (Python Code)

Max Activating Token Index: 966

Text #19

Max Range: 1.3083. Min Range: -1.3083

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1444110 (Python Code)

Max Activating Token Index: 892