Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3005 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0743. Min Act: -0.0003

Data Index: 1493687 (Python Code)

Max Activating Token Index: 838

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0731. Min Act: -0.0003

Data Index: 708544 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0003

Data Index: 1642514 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0712. Min Act: -0.0003

Data Index: 656559 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1530647 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1246470 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1575576 (Python Code)

Max Activating Token Index: 387

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0624. Min Act: -0.0003

Data Index: 649472 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0594. Min Act: -0.0003

Data Index: 795771 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1431487 (Python Code)

Max Activating Token Index: 517

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0605. Min Act: -0.0003

Data Index: 62255 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1510002 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1241384 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1458858 (Python Code)

Max Activating Token Index: 811

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1399770 (Python Code)

Max Activating Token Index: 907

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0531. Min Act: -0.0003

Data Index: 526300 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0569. Min Act: -0.0003

Data Index: 7440 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0545. Min Act: -0.0003

Data Index: 118227 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0574. Min Act: -0.0003

Data Index: 480597 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1437970 (Python Code)

Max Activating Token Index: 106