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

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

Neuron 574 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: 0.2054. Min Range: -0.2054

Max Act: 0.2054. Min Act: -0.0000

Data Index: 102877 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.2046. Min Act: -0.0000

Data Index: 124622 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1950. Min Act: -0.0000

Data Index: 338402 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1814. Min Act: -0.0000

Data Index: 230344 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1734. Min Act: -0.0000

Data Index: 392789 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1248889 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1778. Min Act: -0.0000

Data Index: 39393 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1669. Min Act: -0.0000

Data Index: 667620 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1615. Min Act: -0.0000

Data Index: 341964 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1606. Min Act: -0.0000

Data Index: 915793 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1464. Min Act: -0.0000

Data Index: 56531 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1572. Min Act: -0.0000

Data Index: 735664 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1500. Min Act: -0.0000

Data Index: 144736 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1599. Min Act: -0.0000

Data Index: 807208 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1049784 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1348. Min Act: -0.0000

Data Index: 106846 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1368. Min Act: -0.0000

Data Index: 310988 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1374. Min Act: -0.0000

Data Index: 61213 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1346602 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1403. Min Act: -0.0000

Data Index: 694386 (C4 (Web Text))

Max Activating Token Index: 610