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

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

Neuron 3746 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.3273. Min Act: -0.0001

Data Index: 1530879 (Python Code)

Max Activating Token Index: 345

Text #1

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1303. Min Act: -0.0001

Data Index: 1627954 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.2850. Min Act: -0.0001

Data Index: 1549119 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0182. Min Act: -0.0001

Data Index: 1619475 (Python Code)

Max Activating Token Index: 381

Text #4

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1946. Min Act: -0.0001

Data Index: 1623297 (Python Code)

Max Activating Token Index: 370

Text #5

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0852. Min Act: -0.0001

Data Index: 1442547 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0528. Min Act: -0.0001

Data Index: 1449475 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0812. Min Act: -0.0001

Data Index: 1542089 (Python Code)

Max Activating Token Index: 630

Text #8

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0404. Min Act: -0.0001

Data Index: 1607196 (Python Code)

Max Activating Token Index: 868

Text #9

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0641. Min Act: -0.0001

Data Index: 1361079 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0796. Min Act: -0.0001

Data Index: 1607934 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1822. Min Act: -0.0001

Data Index: 1640098 (Python Code)

Max Activating Token Index: 711

Text #12

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9649. Min Act: -0.0001

Data Index: 1655346 (Python Code)

Max Activating Token Index: 606

Text #13

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9677. Min Act: -0.0001

Data Index: 1378876 (Python Code)

Max Activating Token Index: 200

Text #14

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9675. Min Act: -0.0001

Data Index: 1604956 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0547. Min Act: -0.0001

Data Index: 1526080 (Python Code)

Max Activating Token Index: 600

Text #16

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0107. Min Act: -0.0001

Data Index: 1605329 (Python Code)

Max Activating Token Index: 320

Text #17

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1546424 (Python Code)

Max Activating Token Index: 373

Text #18

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9555. Min Act: -0.0001

Data Index: 1599365 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9792. Min Act: -0.0001

Data Index: 1544750 (Python Code)

Max Activating Token Index: 367