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

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

Neuron 4862 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1512241 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1534863 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1594189 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1601637 (Python Code)

Max Activating Token Index: 520

Text #4

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0839. Min Act: -0.0003

Data Index: 1395377 (Python Code)

Max Activating Token Index: 493

Text #5

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1375412 (Python Code)

Max Activating Token Index: 449

Text #6

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1424088 (Python Code)

Max Activating Token Index: 748

Text #7

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0766. Min Act: -0.0003

Data Index: 1433020 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0784. Min Act: -0.0003

Data Index: 1495098 (Python Code)

Max Activating Token Index: 153

Text #9

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1506455 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1461373 (Python Code)

Max Activating Token Index: 306

Text #11

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1435823 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1523214 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1386085 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1371377 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1470243 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1602870 (Python Code)

Max Activating Token Index: 312

Text #17

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1430885 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1505160 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1629315 (Python Code)

Max Activating Token Index: 34