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

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

Neuron 4079 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: 2.3767. Min Range: -2.3767

Max Act: 2.3767. Min Act: -0.0000

Data Index: 1584855 (Python Code)

Max Activating Token Index: 159

Text #1

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.9516. Min Act: -0.0000

Data Index: 1480267 (Python Code)

Max Activating Token Index: 909

Text #2

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.5973. Min Act: -0.0000

Data Index: 1509473 (Python Code)

Max Activating Token Index: 287

Text #3

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.6688. Min Act: -0.0000

Data Index: 1629914 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.6582. Min Act: -0.0000

Data Index: 1566658 (Python Code)

Max Activating Token Index: 700

Text #5

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.5608. Min Act: -0.0000

Data Index: 1501601 (Python Code)

Max Activating Token Index: 284

Text #6

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.6423. Min Act: -0.0000

Data Index: 1433433 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.6266. Min Act: -0.0000

Data Index: 1480939 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.5547. Min Act: -0.0000

Data Index: 1506607 (Python Code)

Max Activating Token Index: 149

Text #9

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1460183 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1604288 (Python Code)

Max Activating Token Index: 169

Text #11

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1488874 (Python Code)

Max Activating Token Index: 949

Text #12

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.5036. Min Act: -0.0000

Data Index: 1446443 (Python Code)

Max Activating Token Index: 701

Text #13

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.4480. Min Act: -0.0000

Data Index: 1600553 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1377093 (Python Code)

Max Activating Token Index: 613

Text #15

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.4456. Min Act: -0.0000

Data Index: 1483551 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.5496. Min Act: -0.0000

Data Index: 1364422 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.4064. Min Act: -0.0000

Data Index: 1373058 (Python Code)

Max Activating Token Index: 629

Text #18

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.3844. Min Act: -0.0000

Data Index: 1610856 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 2.3767. Min Range: -2.3767

Max Act: 1.3779. Min Act: -0.0000

Data Index: 1584314 (Python Code)

Max Activating Token Index: 257