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

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

Neuron 6060 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3387. Min Range: -2.3387

Max Act: 2.3387. Min Act: -0.0000

Data Index: 1452537 (Python Code)

Max Activating Token Index: 363

Text #1

Max Range: 2.3387. Min Range: -2.3387

Max Act: 2.1152. Min Act: -0.0000

Data Index: 1508808 (Python Code)

Max Activating Token Index: 784

Text #2

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.9375. Min Act: -0.0000

Data Index: 1361994 (Python Code)

Max Activating Token Index: 157

Text #3

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.9236. Min Act: -0.0000

Data Index: 1596214 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.8123. Min Act: -0.0000

Data Index: 1490632 (Python Code)

Max Activating Token Index: 303

Text #5

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.6953. Min Act: -0.0000

Data Index: 1363326 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.6739. Min Act: -0.0000

Data Index: 1449944 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.4947. Min Act: -0.0000

Data Index: 1503773 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.5437. Min Act: -0.0000

Data Index: 1617237 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1518424 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.6254. Min Act: -0.0000

Data Index: 1539699 (Python Code)

Max Activating Token Index: 163

Text #11

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.6128. Min Act: -0.0000

Data Index: 1631518 (Python Code)

Max Activating Token Index: 723

Text #12

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.5223. Min Act: -0.0000

Data Index: 1379710 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.3621. Min Act: -0.0000

Data Index: 1508801 (Python Code)

Max Activating Token Index: 754

Text #14

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.4525. Min Act: -0.0000

Data Index: 1577967 (Python Code)

Max Activating Token Index: 885

Text #15

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.5263. Min Act: -0.0000

Data Index: 1462699 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1538602 (Python Code)

Max Activating Token Index: 69

Text #17

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1488835 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.3113. Min Act: -0.0000

Data Index: 1568215 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 2.3387. Min Range: -2.3387

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1462337 (Python Code)

Max Activating Token Index: 294