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

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

Neuron 1175 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0387. Min Act: -0.0002

Data Index: 816844 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0377. Min Act: -0.0002

Data Index: 330734 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0367. Min Act: -0.0002

Data Index: 763823 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0364. Min Act: -0.0002

Data Index: 104340 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1132139 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0329. Min Act: -0.0002

Data Index: 501952 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1231071 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0304. Min Act: -0.0002

Data Index: 810907 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0310. Min Act: -0.0002

Data Index: 878105 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1443966 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1205464 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0298. Min Act: -0.0002

Data Index: 122664 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1248056 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0277. Min Act: -0.0002

Data Index: 986026 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1392775 (Python Code)

Max Activating Token Index: 131

Text #15

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0275. Min Act: -0.0002

Data Index: 883120 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0273. Min Act: -0.0002

Data Index: 31270 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1262452 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0282. Min Act: -0.0002

Data Index: 190778 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0276. Min Act: -0.0002

Data Index: 756389 (C4 (Web Text))

Max Activating Token Index: 593