Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1177 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0387. Min Act: -0.0005

Data Index: 870521 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0338. Min Act: -0.0005

Data Index: 1273395 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0322. Min Act: -0.0005

Data Index: 223450 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0328. Min Act: -0.0005

Data Index: 1086157 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0314. Min Act: -0.0005

Data Index: 909872 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0314. Min Act: -0.0005

Data Index: 171181 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0324. Min Act: -0.0005

Data Index: 1229034 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0302. Min Act: -0.0005

Data Index: 646070 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0315. Min Act: -0.0005

Data Index: 506629 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0301. Min Act: -0.0005

Data Index: 1327987 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0301. Min Act: -0.0005

Data Index: 457490 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0307. Min Act: -0.0005

Data Index: 567847 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0281. Min Act: -0.0005

Data Index: 497666 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0297. Min Act: -0.0005

Data Index: 1009627 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0299. Min Act: -0.0005

Data Index: 1100163 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0306. Min Act: -0.0005

Data Index: 1199326 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0295. Min Act: -0.0005

Data Index: 805554 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0293. Min Act: -0.0005

Data Index: 364401 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0297. Min Act: -0.0005

Data Index: 52298 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0387. Min Range: -0.0387

Max Act: 0.0291. Min Act: -0.0005

Data Index: 1094231 (C4 (Web Text))

Max Activating Token Index: 10