Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1970 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.4387. Min Act: -0.0002

Data Index: 1377640 (Python Code)

Max Activating Token Index: 370

Text #1

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3927. Min Act: -0.0002

Data Index: 1638120 (Python Code)

Max Activating Token Index: 347

Text #2

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3595. Min Act: -0.0002

Data Index: 1571364 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3633. Min Act: -0.0002

Data Index: 1470925 (Python Code)

Max Activating Token Index: 174

Text #4

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3320. Min Act: -0.0002

Data Index: 1614521 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2965. Min Act: -0.0002

Data Index: 1451078 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3236. Min Act: -0.0002

Data Index: 1485961 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3145. Min Act: -0.0002

Data Index: 1423673 (Python Code)

Max Activating Token Index: 311

Text #8

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3081. Min Act: -0.0002

Data Index: 1468040 (Python Code)

Max Activating Token Index: 917

Text #9

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2966. Min Act: -0.0002

Data Index: 1393866 (Python Code)

Max Activating Token Index: 857

Text #10

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2956. Min Act: -0.0002

Data Index: 1515149 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3089. Min Act: -0.0002

Data Index: 1465076 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3112. Min Act: -0.0002

Data Index: 1568557 (Python Code)

Max Activating Token Index: 990

Text #13

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3092. Min Act: -0.0002

Data Index: 1612359 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2970. Min Act: -0.0002

Data Index: 1641805 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2912. Min Act: -0.0002

Data Index: 1479182 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2801. Min Act: -0.0002

Data Index: 1617271 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2908. Min Act: -0.0002

Data Index: 1396191 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2666. Min Act: -0.0002

Data Index: 1376547 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2912. Min Act: -0.0002

Data Index: 1609280 (Python Code)

Max Activating Token Index: 365