Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3048 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5422. Min Act: -0.0003

Data Index: 1393958 (Python Code)

Max Activating Token Index: 833

Text #1

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5027. Min Act: -0.0003

Data Index: 1544264 (Python Code)

Max Activating Token Index: 530

Text #2

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5117. Min Act: -0.0003

Data Index: 1496038 (Python Code)

Max Activating Token Index: 266

Text #3

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5610. Min Act: -0.0003

Data Index: 1604810 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5084. Min Act: -0.0003

Data Index: 1470995 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5386. Min Act: -0.0003

Data Index: 1477600 (Python Code)

Max Activating Token Index: 861

Text #6

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4782. Min Act: -0.0003

Data Index: 1517867 (Python Code)

Max Activating Token Index: 358

Text #7

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4924. Min Act: -0.0003

Data Index: 1502482 (Python Code)

Max Activating Token Index: 954

Text #8

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5739. Min Act: -0.0003

Data Index: 1650454 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4607. Min Act: -0.0003

Data Index: 1474225 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5004. Min Act: -0.0003

Data Index: 1625591 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5151. Min Act: -0.0003

Data Index: 1407898 (Python Code)

Max Activating Token Index: 902

Text #12

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4618. Min Act: -0.0003

Data Index: 1545899 (Python Code)

Max Activating Token Index: 879

Text #13

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5428. Min Act: -0.0003

Data Index: 1426187 (Python Code)

Max Activating Token Index: 732

Text #14

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5037. Min Act: -0.0003

Data Index: 1482962 (Python Code)

Max Activating Token Index: 275

Text #15

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4574. Min Act: -0.0003

Data Index: 1453057 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4861. Min Act: -0.0003

Data Index: 1622795 (Python Code)

Max Activating Token Index: 158

Text #17

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5160. Min Act: -0.0003

Data Index: 1485906 (Python Code)

Max Activating Token Index: 348

Text #18

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5167. Min Act: -0.0003

Data Index: 1476092 (Python Code)

Max Activating Token Index: 572

Text #19

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4333. Min Act: -0.0003

Data Index: 1620284 (Python Code)

Max Activating Token Index: 199