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

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

Neuron 5996 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3387. Min Range: -7.3387

Max Act: 7.1693. Min Act: -0.0000

Data Index: 1625961 (Python Code)

Max Activating Token Index: 257

Text #1

Max Range: 7.3387. Min Range: -7.3387

Max Act: 7.3387. Min Act: -0.0000

Data Index: 1632575 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 7.3387. Min Range: -7.3387

Max Act: 7.2793. Min Act: -0.0000

Data Index: 1386894 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 7.3387. Min Range: -7.3387

Max Act: 7.1998. Min Act: -0.0000

Data Index: 1499640 (Python Code)

Max Activating Token Index: 274

Text #4

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.7314. Min Act: -0.0000

Data Index: 1404867 (Python Code)

Max Activating Token Index: 234

Text #5

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.8207. Min Act: -0.0000

Data Index: 1595748 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.8159. Min Act: -0.0000

Data Index: 1382533 (Python Code)

Max Activating Token Index: 708

Text #7

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.8150. Min Act: -0.0000

Data Index: 1595947 (Python Code)

Max Activating Token Index: 499

Text #8

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.8420. Min Act: -0.0000

Data Index: 1381085 (Python Code)

Max Activating Token Index: 706

Text #9

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.4073. Min Act: -0.0000

Data Index: 1571136 (Python Code)

Max Activating Token Index: 841

Text #10

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.3582. Min Act: -0.0000

Data Index: 1518985 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.2752. Min Act: -0.0000

Data Index: 1624336 (Python Code)

Max Activating Token Index: 1001

Text #12

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.3728. Min Act: -0.0000

Data Index: 1426502 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.1751. Min Act: -0.0000

Data Index: 1387420 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.1366. Min Act: -0.0000

Data Index: 1644338 (Python Code)

Max Activating Token Index: 455

Text #15

Max Range: 7.3387. Min Range: -7.3387

Max Act: 5.9466. Min Act: -0.0000

Data Index: 1553178 (Python Code)

Max Activating Token Index: 200

Text #16

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.4876. Min Act: -0.0000

Data Index: 1537933 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.2409. Min Act: -0.0000

Data Index: 1636939 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 7.3387. Min Range: -7.3387

Max Act: 6.2271. Min Act: -0.0000

Data Index: 1408366 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 7.3387. Min Range: -7.3387

Max Act: 5.8324. Min Act: -0.0000

Data Index: 1602601 (Python Code)

Max Activating Token Index: 733