Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1153 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0387. Min Act: -0.0004

Data Index: 653919 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0345. Min Act: -0.0003

Data Index: 482342 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0329. Min Act: -0.0004

Data Index: 1103714 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0329. Min Act: -0.0003

Data Index: 399438 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1509341 (Python Code)

Max Activating Token Index: 428

Text #5

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0321. Min Act: -0.0003

Data Index: 199041 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0326. Min Act: -0.0003

Data Index: 406837 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0317. Min Act: -0.0003

Data Index: 113295 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1547199 (Python Code)

Max Activating Token Index: 79

Text #9

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0324. Min Act: -0.0003

Data Index: 580223 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0317. Min Act: -0.0003

Data Index: 185097 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0322. Min Act: -0.0003

Data Index: 538093 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0313. Min Act: -0.0003

Data Index: 703380 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1462903 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0320. Min Act: -0.0003

Data Index: 664059 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0324. Min Act: -0.0003

Data Index: 852997 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0317. Min Act: -0.0004

Data Index: 933819 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0317. Min Act: -0.0003

Data Index: 526067 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0315. Min Act: -0.0003

Data Index: 124274 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1143551 (C4 (Web Text))

Max Activating Token Index: 613