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

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

Neuron 81 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: 1.9311. Min Range: -1.9311

Max Act: 1.9311. Min Act: -0.0000

Data Index: 1453574 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.7528. Min Act: -0.0000

Data Index: 1606254 (Python Code)

Max Activating Token Index: 825

Text #2

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.8159. Min Act: -0.0000

Data Index: 1586191 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.8613. Min Act: -0.0000

Data Index: 1613462 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6203. Min Act: -0.0000

Data Index: 1606284 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6857. Min Act: -0.0000

Data Index: 1577655 (Python Code)

Max Activating Token Index: 963

Text #6

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6931. Min Act: -0.0000

Data Index: 1559255 (Python Code)

Max Activating Token Index: 990

Text #7

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6836. Min Act: -0.0000

Data Index: 1527356 (Python Code)

Max Activating Token Index: 754

Text #8

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6616. Min Act: -0.0000

Data Index: 1437962 (Python Code)

Max Activating Token Index: 795

Text #9

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.5724. Min Act: -0.0000

Data Index: 1404973 (Python Code)

Max Activating Token Index: 980

Text #10

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6751. Min Act: -0.0000

Data Index: 1533815 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6171. Min Act: -0.0000

Data Index: 1476344 (Python Code)

Max Activating Token Index: 996

Text #12

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.7520. Min Act: -0.0000

Data Index: 1419386 (Python Code)

Max Activating Token Index: 514

Text #13

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6657. Min Act: -0.0000

Data Index: 1418550 (Python Code)

Max Activating Token Index: 946

Text #14

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.5816. Min Act: -0.0000

Data Index: 1499781 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.5375. Min Act: -0.0000

Data Index: 1563806 (Python Code)

Max Activating Token Index: 857

Text #16

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6406. Min Act: -0.0000

Data Index: 1462811 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6781. Min Act: -0.0000

Data Index: 1650489 (Python Code)

Max Activating Token Index: 476

Text #18

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6519. Min Act: -0.0000

Data Index: 1562819 (Python Code)

Max Activating Token Index: 1020

Text #19

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.6386. Min Act: -0.0000

Data Index: 1517762 (Python Code)

Max Activating Token Index: 643