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

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

Neuron 3697 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3517. Min Range: -1.3517

Max Act: 1.3517. Min Act: -0.0000

Data Index: 843430 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.3517. Min Range: -1.3517

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1368277 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.9525. Min Act: -0.0000

Data Index: 154632 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 1.3517. Min Range: -1.3517

Max Act: 1.0346. Min Act: -0.0000

Data Index: 858140 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.9235. Min Act: -0.0000

Data Index: 97834 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.9239. Min Act: -0.0000

Data Index: 313349 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1420935 (Python Code)

Max Activating Token Index: 821

Text #7

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.8701. Min Act: -0.0000

Data Index: 345884 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.8635. Min Act: -0.0000

Data Index: 123204 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1638414 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.8871. Min Act: -0.0000

Data Index: 84139 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1414782 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1650792 (Python Code)

Max Activating Token Index: 123

Text #13

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.8191. Min Act: -0.0000

Data Index: 846189 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1343966 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.7812. Min Act: -0.0000

Data Index: 422039 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1657046 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.8472. Min Act: -0.0000

Data Index: 936990 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1438806 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 1.3517. Min Range: -1.3517

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1394590 (Python Code)

Max Activating Token Index: 320