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

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

Neuron 4345 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: 2.1838. Min Range: -2.1838

Max Act: 2.1838. Min Act: -0.0000

Data Index: 1509622 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.9063. Min Act: -0.0000

Data Index: 1639001 (Python Code)

Max Activating Token Index: 374

Text #2

Max Range: 2.1838. Min Range: -2.1838

Max Act: 2.1827. Min Act: -0.0000

Data Index: 1432736 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 2.1838. Min Range: -2.1838

Max Act: 2.0372. Min Act: -0.0000

Data Index: 1567164 (Python Code)

Max Activating Token Index: 589

Text #4

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.7693. Min Act: -0.0000

Data Index: 1525751 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.6691. Min Act: -0.0000

Data Index: 1553785 (Python Code)

Max Activating Token Index: 204

Text #6

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.9328. Min Act: -0.0000

Data Index: 1385917 (Python Code)

Max Activating Token Index: 285

Text #7

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.6280. Min Act: -0.0000

Data Index: 1488777 (Python Code)

Max Activating Token Index: 132

Text #8

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.5539. Min Act: -0.0000

Data Index: 1450715 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.5857. Min Act: -0.0001

Data Index: 1596012 (Python Code)

Max Activating Token Index: 946

Text #10

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.6593. Min Act: -0.0000

Data Index: 1498560 (Python Code)

Max Activating Token Index: 388

Text #11

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.7502. Min Act: -0.0000

Data Index: 1649947 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.6288. Min Act: -0.0000

Data Index: 1568630 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.4055. Min Act: -0.0000

Data Index: 1629414 (Python Code)

Max Activating Token Index: 338

Text #14

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.6336. Min Act: -0.0000

Data Index: 1574811 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.5616. Min Act: -0.0000

Data Index: 1555325 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.5581. Min Act: -0.0000

Data Index: 1456906 (Python Code)

Max Activating Token Index: 667

Text #17

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.5044. Min Act: -0.0000

Data Index: 1425785 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.5939. Min Act: -0.0000

Data Index: 1629288 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 2.1838. Min Range: -2.1838

Max Act: 1.2789. Min Act: -0.0001

Data Index: 1553439 (Python Code)

Max Activating Token Index: 401