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

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

Neuron 1414 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.5387. Min Act: -0.0000

Data Index: 165979 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.5143. Min Act: -0.0000

Data Index: 29251 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.5054. Min Act: -0.0000

Data Index: 356843 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.5084. Min Act: -0.0000

Data Index: 815426 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.5025. Min Act: -0.0000

Data Index: 705179 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4820. Min Act: -0.0000

Data Index: 725546 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4965. Min Act: -0.0000

Data Index: 7064 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1227930 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1221391 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4906. Min Act: -0.0000

Data Index: 800940 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4596. Min Act: -0.0000

Data Index: 12411 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4975. Min Act: -0.0000

Data Index: 573709 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1153460 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4457. Min Act: -0.0000

Data Index: 774554 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4695. Min Act: -0.0000

Data Index: 629573 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4637. Min Act: -0.0000

Data Index: 289661 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4770. Min Act: -0.0000

Data Index: 258597 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4537. Min Act: -0.0000

Data Index: 39786 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4423. Min Act: -0.0000

Data Index: 826256 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4572. Min Act: -0.0000

Data Index: 404857 (C4 (Web Text))

Max Activating Token Index: 300