Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3201 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1071223 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1020670 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7833. Min Act: -0.0001

Data Index: 196286 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7821. Min Act: 0.0000

Data Index: 1316044 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7321. Min Act: -0.0000

Data Index: 841949 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7553. Min Act: 0.0000

Data Index: 1166986 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7904. Min Act: -0.0000

Data Index: 749299 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7626. Min Act: -0.0000

Data Index: 490151 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.8093. Min Act: -0.0000

Data Index: 566766 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7782. Min Act: -0.0000

Data Index: 67413 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7804. Min Act: -0.0000

Data Index: 419288 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7888. Min Act: 0.0000

Data Index: 550707 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1110302 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1214465 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7375. Min Act: -0.0000

Data Index: 396901 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7786. Min Act: -0.0000

Data Index: 184197 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7307. Min Act: -0.0000

Data Index: 53478 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7311. Min Act: -0.0001

Data Index: 706937 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7709. Min Act: -0.0000

Data Index: 816021 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.8387. Min Range: -0.8387

Max Act: 0.7264. Min Act: -0.0001

Data Index: 824659 (C4 (Web Text))

Max Activating Token Index: 392