Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4273 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.9077. Min Act: -0.0002

Data Index: 1558267 (Python Code)

Max Activating Token Index: 276

Text #1

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8306. Min Act: -0.0002

Data Index: 1566868 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7669. Min Act: -0.0002

Data Index: 1570502 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8069. Min Act: -0.0002

Data Index: 1487689 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7786. Min Act: -0.0002

Data Index: 1512618 (Python Code)

Max Activating Token Index: 244

Text #5

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8063. Min Act: -0.0002

Data Index: 1553854 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7945. Min Act: -0.0002

Data Index: 1518117 (Python Code)

Max Activating Token Index: 305

Text #7

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7995. Min Act: -0.0002

Data Index: 1452780 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7799. Min Act: -0.0002

Data Index: 1382906 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7962. Min Act: -0.0002

Data Index: 1530259 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8123. Min Act: -0.0002

Data Index: 1570582 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7826. Min Act: -0.0002

Data Index: 1609535 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7665. Min Act: -0.0002

Data Index: 1596768 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7778. Min Act: -0.0002

Data Index: 1605743 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7813. Min Act: -0.0002

Data Index: 1464590 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7708. Min Act: -0.0002

Data Index: 1444659 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7727. Min Act: -0.0002

Data Index: 1385019 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7754. Min Act: -0.0002

Data Index: 1567742 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7722. Min Act: -0.0002

Data Index: 1479179 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7405. Min Act: -0.0002

Data Index: 1589916 (Python Code)

Max Activating Token Index: 23