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

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

Neuron 291 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: 3.0084. Min Range: -3.0084

Max Act: 2.8900. Min Act: -0.0000

Data Index: 1401495 (Python Code)

Max Activating Token Index: 325

Text #1

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.8816. Min Act: -0.0000

Data Index: 1533509 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.7766. Min Act: -0.0000

Data Index: 1597254 (Python Code)

Max Activating Token Index: 648

Text #3

Max Range: 3.0084. Min Range: -3.0084

Max Act: 3.0084. Min Act: -0.0000

Data Index: 1495683 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.5703. Min Act: -0.0000

Data Index: 1574534 (Python Code)

Max Activating Token Index: 33

Text #5

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.9039. Min Act: -0.0000

Data Index: 1362271 (Python Code)

Max Activating Token Index: 555

Text #6

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.6660. Min Act: -0.0000

Data Index: 1538209 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.7968. Min Act: -0.0000

Data Index: 1432930 (Python Code)

Max Activating Token Index: 534

Text #8

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.6358. Min Act: -0.0000

Data Index: 1648809 (Python Code)

Max Activating Token Index: 238

Text #9

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.6110. Min Act: -0.0000

Data Index: 1651771 (Python Code)

Max Activating Token Index: 709

Text #10

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.6218. Min Act: -0.0000

Data Index: 1365264 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.7129. Min Act: -0.0000

Data Index: 1449164 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.7534. Min Act: -0.0000

Data Index: 1601609 (Python Code)

Max Activating Token Index: 778

Text #13

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.6528. Min Act: -0.0000

Data Index: 1602246 (Python Code)

Max Activating Token Index: 314

Text #14

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.6635. Min Act: -0.0000

Data Index: 1641231 (Python Code)

Max Activating Token Index: 599

Text #15

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.5836. Min Act: -0.0000

Data Index: 1613746 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.5912. Min Act: -0.0000

Data Index: 1472206 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.5673. Min Act: -0.0000

Data Index: 1369124 (Python Code)

Max Activating Token Index: 589

Text #18

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.8212. Min Act: -0.0000

Data Index: 1561454 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 3.0084. Min Range: -3.0084

Max Act: 2.4223. Min Act: -0.0000

Data Index: 1639940 (Python Code)

Max Activating Token Index: 3