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

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

Neuron 105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0555. Min Range: -1.0555

Max Act: 1.0482. Min Act: -0.0001

Data Index: 1553201 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9307. Min Act: -0.0001

Data Index: 1566610 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 1.0555. Min Range: -1.0555

Max Act: 1.0387. Min Act: -0.0001

Data Index: 1648859 (Python Code)

Max Activating Token Index: 578

Text #3

Max Range: 1.0555. Min Range: -1.0555

Max Act: 1.0295. Min Act: -0.0001

Data Index: 1637329 (Python Code)

Max Activating Token Index: 66

Text #4

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9803. Min Act: -0.0001

Data Index: 196067 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 1.0555. Min Range: -1.0555

Max Act: 1.0555. Min Act: -0.0001

Data Index: 1555158 (Python Code)

Max Activating Token Index: 263

Text #6

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9286. Min Act: -0.0001

Data Index: 1585232 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9857. Min Act: -0.0001

Data Index: 1409847 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9168. Min Act: -0.0001

Data Index: 1527287 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8389. Min Act: -0.0001

Data Index: 1552058 (Python Code)

Max Activating Token Index: 922

Text #10

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9248. Min Act: -0.0001

Data Index: 1573504 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8907. Min Act: -0.0001

Data Index: 1566815 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8907. Min Act: -0.0001

Data Index: 1388277 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8907. Min Act: -0.0001

Data Index: 1372791 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9844. Min Act: -0.0001

Data Index: 290134 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8829. Min Act: -0.0001

Data Index: 1555752 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8829. Min Act: -0.0001

Data Index: 1578325 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8901. Min Act: -0.0001

Data Index: 1554086 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9647. Min Act: -0.0001

Data Index: 1467850 (Python Code)

Max Activating Token Index: 867

Text #19

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8744. Min Act: -0.0001

Data Index: 1521140 (Python Code)

Max Activating Token Index: 675