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

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

Neuron 1451 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: 3.1035. Min Range: -3.1035

Max Act: 3.1035. Min Act: -0.0000

Data Index: 1552404 (Python Code)

Max Activating Token Index: 459

Text #1

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.2367. Min Act: -0.0001

Data Index: 1518213 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.0751. Min Act: -0.0001

Data Index: 1384116 (Python Code)

Max Activating Token Index: 945

Text #3

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.0735. Min Act: -0.0000

Data Index: 1457319 (Python Code)

Max Activating Token Index: 89

Text #4

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.0552. Min Act: -0.0001

Data Index: 1528810 (Python Code)

Max Activating Token Index: 218

Text #5

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.9853. Min Act: -0.0001

Data Index: 1590216 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.9853. Min Act: -0.0000

Data Index: 1462568 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.8691. Min Act: -0.0000

Data Index: 1596306 (Python Code)

Max Activating Token Index: 400

Text #8

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.8413. Min Act: -0.0000

Data Index: 1558894 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.8239. Min Act: -0.0000

Data Index: 1582456 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.8239. Min Act: -0.0000

Data Index: 1580251 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 3.1035. Min Range: -3.1035

Max Act: 2.0140. Min Act: -0.0001

Data Index: 1606798 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.8544. Min Act: -0.0000

Data Index: 1601762 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.7505. Min Act: -0.0000

Data Index: 1391609 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.7368. Min Act: -0.0001

Data Index: 1602937 (Python Code)

Max Activating Token Index: 973

Text #15

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.6986. Min Act: -0.0000

Data Index: 1489469 (Python Code)

Max Activating Token Index: 219

Text #16

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.8647. Min Act: -0.0001

Data Index: 1525464 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.8489. Min Act: -0.0001

Data Index: 1563157 (Python Code)

Max Activating Token Index: 232

Text #18

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.6447. Min Act: -0.0000

Data Index: 1379548 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 3.1035. Min Range: -3.1035

Max Act: 1.6687. Min Act: -0.0001

Data Index: 1569288 (Python Code)

Max Activating Token Index: 6