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

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

Neuron 5512 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.9269. Min Act: -0.0000

Data Index: 1410363 (Python Code)

Max Activating Token Index: 104

Text #1

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.9197. Min Act: -0.0000

Data Index: 1634514 (Python Code)

Max Activating Token Index: 650

Text #2

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.6908. Min Act: -0.0000

Data Index: 1462232 (Python Code)

Max Activating Token Index: 467

Text #3

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.7229. Min Act: -0.0000

Data Index: 1445159 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.6781. Min Act: -0.0000

Data Index: 1656911 (Python Code)

Max Activating Token Index: 668

Text #5

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.7130. Min Act: -0.0000

Data Index: 1512916 (Python Code)

Max Activating Token Index: 896

Text #6

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.6023. Min Act: -0.0000

Data Index: 1579063 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.6513. Min Act: -0.0000

Data Index: 1537621 (Python Code)

Max Activating Token Index: 960

Text #8

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.6180. Min Act: -0.0000

Data Index: 1471463 (Python Code)

Max Activating Token Index: 685

Text #9

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.6075. Min Act: -0.0000

Data Index: 655501 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.5375. Min Act: -0.0000

Data Index: 1402686 (Python Code)

Max Activating Token Index: 345

Text #11

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.5003. Min Act: -0.0000

Data Index: 1439363 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1570243 (Python Code)

Max Activating Token Index: 383

Text #13

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.5930. Min Act: -0.0000

Data Index: 1561483 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.5419. Min Act: -0.0000

Data Index: 1604511 (Python Code)

Max Activating Token Index: 861

Text #15

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.5822. Min Act: -0.0000

Data Index: 1474561 (Python Code)

Max Activating Token Index: 299

Text #16

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.5281. Min Act: -0.0000

Data Index: 1581586 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.5082. Min Act: -0.0000

Data Index: 877902 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1372879 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 1.9269. Min Range: -1.9269

Max Act: 1.4510. Min Act: -0.0000

Data Index: 1530246 (Python Code)

Max Activating Token Index: 826