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

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

Neuron 4201 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1440291 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1477724 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1569852 (Python Code)

Max Activating Token Index: 966

Text #3

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1413095 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1643900 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1507821 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1539278 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0783. Min Act: -0.0000

Data Index: 1648254 (Python Code)

Max Activating Token Index: 322

Text #8

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1361358 (Python Code)

Max Activating Token Index: 608

Text #9

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1469248 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1066488 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0745. Min Act: -0.0000

Data Index: 1371852 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1367932 (Python Code)

Max Activating Token Index: 392

Text #13

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1487939 (Python Code)

Max Activating Token Index: 414

Text #14

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1640877 (Python Code)

Max Activating Token Index: 218

Text #15

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0758. Min Act: -0.0000

Data Index: 452369 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1567457 (Python Code)

Max Activating Token Index: 600

Text #17

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1548819 (Python Code)

Max Activating Token Index: 930

Text #18

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1470447 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0788. Min Act: -0.0000

Data Index: 176656 (C4 (Web Text))

Max Activating Token Index: 816