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

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

Neuron 1593 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0992. Min Range: -2.0992

Max Act: 2.0679. Min Act: -0.0000

Data Index: 1593267 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 2.0992. Min Range: -2.0992

Max Act: 2.0992. Min Act: -0.0001

Data Index: 1506483 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8852. Min Act: -0.0000

Data Index: 1537720 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.9643. Min Act: -0.0000

Data Index: 1484051 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8943. Min Act: -0.0000

Data Index: 1473613 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.9848. Min Act: -0.0000

Data Index: 1577345 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.9128. Min Act: -0.0000

Data Index: 1540033 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8819. Min Act: -0.0000

Data Index: 1364486 (Python Code)

Max Activating Token Index: 75

Text #8

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.9024. Min Act: -0.0000

Data Index: 1651942 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.9362. Min Act: -0.0000

Data Index: 1624417 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8631. Min Act: -0.0001

Data Index: 1427114 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.9265. Min Act: -0.0000

Data Index: 1444870 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8663. Min Act: -0.0000

Data Index: 1564866 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8612. Min Act: -0.0000

Data Index: 1374095 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8160. Min Act: -0.0000

Data Index: 1530815 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.7846. Min Act: -0.0000

Data Index: 1477004 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8481. Min Act: -0.0000

Data Index: 1471559 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.7285. Min Act: -0.0000

Data Index: 1522827 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8012. Min Act: -0.0000

Data Index: 1626306 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 2.0992. Min Range: -2.0992

Max Act: 1.8078. Min Act: -0.0000

Data Index: 1459658 (Python Code)

Max Activating Token Index: 85