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

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

Neuron 2036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0387. Min Range: -6.0387

Max Act: 6.0387. Min Act: -0.0000

Data Index: 1390529 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.9762. Min Act: -0.0000

Data Index: 1375970 (Python Code)

Max Activating Token Index: 249

Text #2

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.7256. Min Act: -0.0000

Data Index: 1412392 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.9227. Min Act: -0.0000

Data Index: 1561085 (Python Code)

Max Activating Token Index: 251

Text #4

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.8579. Min Act: -0.0000

Data Index: 1553028 (Python Code)

Max Activating Token Index: 663

Text #5

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.7172. Min Act: -0.0000

Data Index: 1639165 (Python Code)

Max Activating Token Index: 225

Text #6

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.8194. Min Act: -0.0000

Data Index: 1618779 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.4205. Min Act: -0.0001

Data Index: 1557995 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.2767. Min Act: -0.0000

Data Index: 1388220 (Python Code)

Max Activating Token Index: 773

Text #9

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.5850. Min Act: -0.0000

Data Index: 1635391 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.6806. Min Act: -0.0000

Data Index: 1584250 (Python Code)

Max Activating Token Index: 719

Text #11

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.6664. Min Act: -0.0000

Data Index: 1454023 (Python Code)

Max Activating Token Index: 79

Text #12

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.3817. Min Act: -0.0000

Data Index: 1472949 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.2281. Min Act: -0.0000

Data Index: 1399267 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.1506. Min Act: -0.0000

Data Index: 1389794 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.2964. Min Act: -0.0000

Data Index: 1627741 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 6.0387. Min Range: -6.0387

Max Act: 5.1212. Min Act: -0.0000

Data Index: 1529720 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 6.0387. Min Range: -6.0387

Max Act: 4.9235. Min Act: -0.0000

Data Index: 1425919 (Python Code)

Max Activating Token Index: 233

Text #18

Max Range: 6.0387. Min Range: -6.0387

Max Act: 4.8779. Min Act: -0.0000

Data Index: 1614024 (Python Code)

Max Activating Token Index: 428

Text #19

Max Range: 6.0387. Min Range: -6.0387

Max Act: 4.8558. Min Act: -0.0000

Data Index: 1605450 (Python Code)

Max Activating Token Index: 718