Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1733 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0948. Min Range: -1.0948

Max Act: 1.0948. Min Act: -0.0001

Data Index: 1459510 (Python Code)

Max Activating Token Index: 645

Text #1

Max Range: 1.0948. Min Range: -1.0948

Max Act: 1.0343. Min Act: -0.0001

Data Index: 1518138 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.9724. Min Act: -0.0001

Data Index: 1396404 (Python Code)

Max Activating Token Index: 250

Text #3

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8810. Min Act: -0.0001

Data Index: 1556083 (Python Code)

Max Activating Token Index: 881

Text #4

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8853. Min Act: -0.0001

Data Index: 1460922 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1619722 (Python Code)

Max Activating Token Index: 574

Text #6

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8269. Min Act: -0.0001

Data Index: 1586275 (Python Code)

Max Activating Token Index: 363

Text #7

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7869. Min Act: -0.0001

Data Index: 1647888 (Python Code)

Max Activating Token Index: 76

Text #8

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7635. Min Act: -0.0001

Data Index: 1586622 (Python Code)

Max Activating Token Index: 417

Text #9

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7301. Min Act: -0.0001

Data Index: 1510194 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7013. Min Act: -0.0001

Data Index: 1553664 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8148. Min Act: -0.0001

Data Index: 1618319 (Python Code)

Max Activating Token Index: 610

Text #12

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6791. Min Act: -0.0001

Data Index: 1380242 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6985. Min Act: -0.0001

Data Index: 1616864 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6718. Min Act: -0.0001

Data Index: 1539648 (Python Code)

Max Activating Token Index: 915

Text #15

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7071. Min Act: -0.0001

Data Index: 1367932 (Python Code)

Max Activating Token Index: 229

Text #16

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6935. Min Act: -0.0001

Data Index: 1587937 (Python Code)

Max Activating Token Index: 636

Text #17

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6168. Min Act: -0.0001

Data Index: 1503478 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6693. Min Act: -0.0001

Data Index: 1474446 (Python Code)

Max Activating Token Index: 109

Text #19

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6331. Min Act: -0.0001

Data Index: 1410306 (Python Code)

Max Activating Token Index: 1017