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

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

Neuron 4695 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0032. Min Range: -1.0032

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1492289 (Python Code)

Max Activating Token Index: 809

Text #1

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8609. Min Act: -0.0000

Data Index: 1483443 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1583431 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1480914 (Python Code)

Max Activating Token Index: 160

Text #4

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1366798 (Python Code)

Max Activating Token Index: 982

Text #5

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1370060 (Python Code)

Max Activating Token Index: 792

Text #6

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1605248 (Python Code)

Max Activating Token Index: 344

Text #7

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1558393 (Python Code)

Max Activating Token Index: 596

Text #8

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1630198 (Python Code)

Max Activating Token Index: 671

Text #9

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1602670 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1381633 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1437977 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1568367 (Python Code)

Max Activating Token Index: 218

Text #13

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1637770 (Python Code)

Max Activating Token Index: 351

Text #14

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1607177 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1397079 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1521699 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1557068 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1570461 (Python Code)

Max Activating Token Index: 896

Text #19

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1645798 (Python Code)

Max Activating Token Index: 245