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

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

Neuron 4306 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: 1.0841. Min Range: -1.0841

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1424973 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 1.0841. Min Range: -1.0841

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1384569 (Python Code)

Max Activating Token Index: 829

Text #2

Max Range: 1.0841. Min Range: -1.0841

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1469133 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 1.0841. Min Range: -1.0841

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1569528 (Python Code)

Max Activating Token Index: 519

Text #4

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1406933 (Python Code)

Max Activating Token Index: 240

Text #5

Max Range: 1.0841. Min Range: -1.0841

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1565253 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 1.0841. Min Range: -1.0841

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1416919 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1654373 (Python Code)

Max Activating Token Index: 663

Text #8

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1391882 (Python Code)

Max Activating Token Index: 647

Text #9

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1427673 (Python Code)

Max Activating Token Index: 352

Text #10

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1572930 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1460747 (Python Code)

Max Activating Token Index: 760

Text #12

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1537935 (Python Code)

Max Activating Token Index: 804

Text #13

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1629585 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1553374 (Python Code)

Max Activating Token Index: 968

Text #15

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1641131 (Python Code)

Max Activating Token Index: 730

Text #16

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1632590 (Python Code)

Max Activating Token Index: 315

Text #17

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1566729 (Python Code)

Max Activating Token Index: 697

Text #18

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1548960 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 1.0841. Min Range: -1.0841

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1390371 (Python Code)

Max Activating Token Index: 585