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

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

Neuron 3708 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9087. Min Range: -3.9087

Max Act: 3.9087. Min Act: 0.0000

Data Index: 1481754 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.9082. Min Act: -0.0000

Data Index: 1583370 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.3412. Min Act: -0.0000

Data Index: 1630653 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.3113. Min Act: -0.0000

Data Index: 1450786 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.3704. Min Act: -0.0000

Data Index: 1460564 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.0919. Min Act: -0.0000

Data Index: 1430046 (Python Code)

Max Activating Token Index: 231

Text #6

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.1327. Min Act: -0.0000

Data Index: 1420065 (Python Code)

Max Activating Token Index: 945

Text #7

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.1293. Min Act: -0.0000

Data Index: 1529381 (Python Code)

Max Activating Token Index: 209

Text #8

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.0004. Min Act: -0.0000

Data Index: 1470040 (Python Code)

Max Activating Token Index: 917

Text #9

Max Range: 3.9087. Min Range: -3.9087

Max Act: 1.8751. Min Act: -0.0000

Data Index: 1496722 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.0596. Min Act: 0.0000

Data Index: 1598699 (Python Code)

Max Activating Token Index: 648

Text #11

Max Range: 3.9087. Min Range: -3.9087

Max Act: 1.9408. Min Act: -0.0000

Data Index: 1557908 (Python Code)

Max Activating Token Index: 322

Text #12

Max Range: 3.9087. Min Range: -3.9087

Max Act: 2.0493. Min Act: -0.0000

Data Index: 1417123 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 3.9087. Min Range: -3.9087

Max Act: 1.9199. Min Act: -0.0000

Data Index: 1365830 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 3.9087. Min Range: -3.9087

Max Act: 1.8123. Min Act: -0.0000

Data Index: 1515904 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 3.9087. Min Range: -3.9087

Max Act: 1.8189. Min Act: -0.0000

Data Index: 1600892 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 3.9087. Min Range: -3.9087

Max Act: 1.7968. Min Act: 0.0000

Data Index: 1570175 (Python Code)

Max Activating Token Index: 935

Text #17

Max Range: 3.9087. Min Range: -3.9087

Max Act: 1.8629. Min Act: 0.0001

Data Index: 1651420 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 3.9087. Min Range: -3.9087

Max Act: 1.8098. Min Act: -0.0000

Data Index: 1647246 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 3.9087. Min Range: -3.9087

Max Act: 1.7961. Min Act: -0.0000

Data Index: 1446429 (Python Code)

Max Activating Token Index: 725