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

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

Neuron 3416 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: 0.3387. Min Range: -0.3387

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1054800 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.3097. Min Act: -0.0000

Data Index: 749427 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.3131. Min Act: -0.0000

Data Index: 326459 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2895. Min Act: -0.0000

Data Index: 430224 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1326051 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2969. Min Act: -0.0000

Data Index: 33357 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2940. Min Act: -0.0000

Data Index: 690018 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2706. Min Act: -0.0000

Data Index: 210691 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.3018. Min Act: -0.0000

Data Index: 221314 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1200103 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2764. Min Act: -0.0000

Data Index: 309161 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2554. Min Act: -0.0000

Data Index: 565809 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2716. Min Act: -0.0000

Data Index: 365312 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2718. Min Act: -0.0000

Data Index: 895714 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2771. Min Act: -0.0000

Data Index: 96592 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1219511 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2544. Min Act: -0.0000

Data Index: 258681 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2693. Min Act: -0.0000

Data Index: 693932 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2598. Min Act: -0.0000

Data Index: 460038 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.3387. Min Range: -0.3387

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1085266 (C4 (Web Text))

Max Activating Token Index: 354