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

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

Neuron 4316 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1799. Min Range: -2.1799

Max Act: 2.0809. Min Act: -0.0000

Data Index: 1485351 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 2.1799. Min Range: -2.1799

Max Act: 2.1799. Min Act: -0.0000

Data Index: 1649315 (Python Code)

Max Activating Token Index: 179

Text #2

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.9963. Min Act: -0.0000

Data Index: 1374180 (Python Code)

Max Activating Token Index: 661

Text #3

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.9551. Min Act: -0.0000

Data Index: 1545978 (Python Code)

Max Activating Token Index: 907

Text #4

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.8982. Min Act: -0.0000

Data Index: 1368060 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.8459. Min Act: -0.0000

Data Index: 1403865 (Python Code)

Max Activating Token Index: 698

Text #6

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.8738. Min Act: -0.0000

Data Index: 1487614 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1369922 (Python Code)

Max Activating Token Index: 772

Text #8

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.7993. Min Act: 0.0000

Data Index: 1553843 (Python Code)

Max Activating Token Index: 667

Text #9

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.7815. Min Act: -0.0000

Data Index: 1644233 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.6530. Min Act: -0.0000

Data Index: 1654724 (Python Code)

Max Activating Token Index: 122

Text #11

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.7324. Min Act: -0.0000

Data Index: 1408821 (Python Code)

Max Activating Token Index: 804

Text #12

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.6702. Min Act: -0.0000

Data Index: 1535681 (Python Code)

Max Activating Token Index: 866

Text #13

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.7251. Min Act: -0.0000

Data Index: 1596219 (Python Code)

Max Activating Token Index: 561

Text #14

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.6610. Min Act: 0.0000

Data Index: 1371039 (Python Code)

Max Activating Token Index: 624

Text #15

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.6251. Min Act: -0.0000

Data Index: 1605017 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.6768. Min Act: -0.0000

Data Index: 1437421 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.7189. Min Act: -0.0000

Data Index: 1537462 (Python Code)

Max Activating Token Index: 290

Text #18

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.6280. Min Act: -0.0000

Data Index: 1469855 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 2.1799. Min Range: -2.1799

Max Act: 1.6548. Min Act: -0.0000

Data Index: 1501891 (Python Code)

Max Activating Token Index: 14