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

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

Neuron 2007 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1591057 (Python Code)

Max Activating Token Index: 693

Text #1

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1428321 (Python Code)

Max Activating Token Index: 954

Text #2

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8355. Min Act: 0.0000

Data Index: 1648551 (Python Code)

Max Activating Token Index: 553

Text #3

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7846. Min Act: 0.0000

Data Index: 1539046 (Python Code)

Max Activating Token Index: 184

Text #4

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1495831 (Python Code)

Max Activating Token Index: 910

Text #5

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8244. Min Act: 0.0000

Data Index: 1444427 (Python Code)

Max Activating Token Index: 48

Text #6

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1468083 (Python Code)

Max Activating Token Index: 445

Text #7

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1488102 (Python Code)

Max Activating Token Index: 339

Text #8

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7609. Min Act: 0.0000

Data Index: 1568836 (Python Code)

Max Activating Token Index: 735

Text #9

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1447625 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1608609 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1579987 (Python Code)

Max Activating Token Index: 675

Text #12

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1492929 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1455769 (Python Code)

Max Activating Token Index: 955

Text #14

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1615686 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1463484 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1602980 (Python Code)

Max Activating Token Index: 912

Text #17

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1444485 (Python Code)

Max Activating Token Index: 809

Text #18

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1545807 (Python Code)

Max Activating Token Index: 501

Text #19

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1653300 (Python Code)

Max Activating Token Index: 751