Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 799 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.1774. Min Act: -0.0003

Data Index: 1481247 (Python Code)

Max Activating Token Index: 573

Text #1

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8577. Min Act: -0.0003

Data Index: 1512908 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8840. Min Act: -0.0003

Data Index: 1394864 (Python Code)

Max Activating Token Index: 435

Text #3

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8128. Min Act: -0.0003

Data Index: 1549669 (Python Code)

Max Activating Token Index: 845

Text #4

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8643. Min Act: -0.0003

Data Index: 1484184 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8659. Min Act: -0.0003

Data Index: 1374159 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8689. Min Act: -0.0003

Data Index: 1502833 (Python Code)

Max Activating Token Index: 566

Text #7

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8180. Min Act: -0.0003

Data Index: 1428743 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7774. Min Act: -0.0003

Data Index: 1479737 (Python Code)

Max Activating Token Index: 898

Text #9

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7822. Min Act: -0.0003

Data Index: 1549661 (Python Code)

Max Activating Token Index: 812

Text #10

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8236. Min Act: -0.0003

Data Index: 1495509 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8229. Min Act: -0.0003

Data Index: 1649066 (Python Code)

Max Activating Token Index: 516

Text #12

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.6245. Min Act: -0.0003

Data Index: 1414466 (Python Code)

Max Activating Token Index: 592

Text #13

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8100. Min Act: -0.0003

Data Index: 1559904 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8277. Min Act: -0.0003

Data Index: 1519156 (Python Code)

Max Activating Token Index: 125

Text #15

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7514. Min Act: -0.0003

Data Index: 1467431 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8012. Min Act: -0.0003

Data Index: 1536908 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8223. Min Act: -0.0003

Data Index: 1598298 (Python Code)

Max Activating Token Index: 168

Text #18

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7694. Min Act: -0.0003

Data Index: 1402256 (Python Code)

Max Activating Token Index: 59

Text #19

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.7927. Min Act: -0.0003

Data Index: 1621412 (Python Code)

Max Activating Token Index: 212