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

Dataset: The Pile

Neuron 5087 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0000

Data Index: 954417 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0580. Min Act: 0.0000

Data Index: 605329 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0572. Min Act: -0.0000

Data Index: 518098 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0569. Min Act: 0.0000

Data Index: 390450 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0559. Min Act: -0.0000

Data Index: 467986 (The Pile)

Max Activating Token Index: 4

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1706091 (The Pile)

Max Activating Token Index: 4

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0537. Min Act: -0.0000

Data Index: 229570 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0556. Min Act: 0.0000

Data Index: 519103 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0553. Min Act: -0.0000

Data Index: 676929 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0572. Min Act: -0.0000

Data Index: 250924 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0552. Min Act: -0.0000

Data Index: 304358 (The Pile)

Max Activating Token Index: 6

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0546. Min Act: -0.0000

Data Index: 1620770 (The Pile)

Max Activating Token Index: 5

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0542. Min Act: -0.0000

Data Index: 611496 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1354916 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0539. Min Act: -0.0000

Data Index: 471688 (The Pile)

Max Activating Token Index: 5

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0537. Min Act: -0.0000

Data Index: 952604 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0517. Min Act: -0.0000

Data Index: 489666 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0536. Min Act: -0.0000

Data Index: 775616 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0531. Min Act: -0.0000

Data Index: 953040 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1894035 (The Pile)

Max Activating Token Index: 6