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

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

Neuron 1594 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.2387. Min Act: -0.0000

Data Index: 857657 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1976. Min Act: -0.0000

Data Index: 211662 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1910. Min Act: -0.0000

Data Index: 512317 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1131028 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1521. Min Act: -0.0000

Data Index: 413206 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1705. Min Act: -0.0000

Data Index: 459555 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1648. Min Act: -0.0000

Data Index: 109972 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1560. Min Act: -0.0000

Data Index: 952272 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1617. Min Act: -0.0000

Data Index: 547424 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1066428 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1512. Min Act: -0.0000

Data Index: 77257 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1634. Min Act: -0.0000

Data Index: 599728 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1570. Min Act: -0.0000

Data Index: 138916 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1274756 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1567. Min Act: -0.0000

Data Index: 216108 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1054362 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1540. Min Act: -0.0000

Data Index: 726410 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1483. Min Act: -0.0000

Data Index: 530745 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1503. Min Act: -0.0000

Data Index: 486780 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.2387. Min Range: -0.2387

Max Act: 0.1452. Min Act: -0.0000

Data Index: 466668 (C4 (Web Text))

Max Activating Token Index: 596