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

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

Neuron 927 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1781. Min Range: -2.1781

Max Act: 2.0748. Min Act: -0.0000

Data Index: 1441436 (Python Code)

Max Activating Token Index: 451

Text #1

Max Range: 2.1781. Min Range: -2.1781

Max Act: 2.1781. Min Act: -0.0000

Data Index: 1529449 (Python Code)

Max Activating Token Index: 645

Text #2

Max Range: 2.1781. Min Range: -2.1781

Max Act: 2.0988. Min Act: -0.0000

Data Index: 1415155 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.9797. Min Act: -0.0000

Data Index: 1479525 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 2.1781. Min Range: -2.1781

Max Act: 2.1460. Min Act: -0.0000

Data Index: 1449883 (Python Code)

Max Activating Token Index: 222

Text #5

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.9964. Min Act: -0.0000

Data Index: 1551827 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.9412. Min Act: -0.0000

Data Index: 1504340 (Python Code)

Max Activating Token Index: 539

Text #7

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.9259. Min Act: -0.0000

Data Index: 1540152 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.8988. Min Act: -0.0000

Data Index: 1537953 (Python Code)

Max Activating Token Index: 599

Text #9

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.8960. Min Act: -0.0000

Data Index: 1369455 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.9920. Min Act: -0.0000

Data Index: 1362683 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.8812. Min Act: -0.0000

Data Index: 1446753 (Python Code)

Max Activating Token Index: 392

Text #12

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.7786. Min Act: -0.0000

Data Index: 1440976 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1396665 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.9613. Min Act: -0.0000

Data Index: 1485653 (Python Code)

Max Activating Token Index: 957

Text #15

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1396111 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.8999. Min Act: -0.0000

Data Index: 1375469 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.5861. Min Act: -0.0000

Data Index: 859480 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.7662. Min Act: -0.0000

Data Index: 1398390 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 2.1781. Min Range: -2.1781

Max Act: 1.8191. Min Act: -0.0000

Data Index: 1417492 (Python Code)

Max Activating Token Index: 823