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

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

Neuron 2630 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1387. Min Act: -0.0002

Data Index: 1004668 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1111. Min Act: -0.0002

Data Index: 264112 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1032. Min Act: -0.0002

Data Index: 770387 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1010. Min Act: -0.0002

Data Index: 858230 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1007. Min Act: -0.0002

Data Index: 407341 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.1005. Min Act: -0.0002

Data Index: 268394 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1358209 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0910. Min Act: -0.0002

Data Index: 951090 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0897. Min Act: -0.0002

Data Index: 225789 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0895. Min Act: -0.0002

Data Index: 428464 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0925. Min Act: -0.0002

Data Index: 851416 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0824. Min Act: -0.0002

Data Index: 811939 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0877. Min Act: -0.0002

Data Index: 504167 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0849. Min Act: -0.0002

Data Index: 763687 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0846. Min Act: -0.0002

Data Index: 922172 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1357940 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0787. Min Act: -0.0002

Data Index: 672249 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0840. Min Act: -0.0002

Data Index: 570330 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0794. Min Act: -0.0002

Data Index: 239101 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.1387. Min Range: -0.1387

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1093544 (C4 (Web Text))

Max Activating Token Index: 365