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

Dataset: The Pile

Neuron 1936 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.8935. Min Act: -0.0000

Data Index: 1538503 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.9547. Min Act: -0.0000

Data Index: 1627751 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.7200. Min Act: -0.0000

Data Index: 197034 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6135. Min Act: -0.0000

Data Index: 1429554 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.7058. Min Act: -0.0000

Data Index: 1501748 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6731. Min Act: -0.0000

Data Index: 321473 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6635. Min Act: -0.0000

Data Index: 1428341 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6559. Min Act: -0.0000

Data Index: 1165024 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6360. Min Act: -0.0000

Data Index: 570180 (The Pile)

Max Activating Token Index: 150

Text #9

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6081. Min Act: -0.0000

Data Index: 469416 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.6079. Min Act: -0.0000

Data Index: 229424 (The Pile)

Max Activating Token Index: 682

Text #11

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5878. Min Act: -0.0000

Data Index: 100974 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5589. Min Act: -0.0000

Data Index: 178507 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5479. Min Act: -0.0000

Data Index: 187421 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5589. Min Act: -0.0000

Data Index: 1730361 (The Pile)

Max Activating Token Index: 852

Text #15

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1451470 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.5155. Min Act: -0.0000

Data Index: 430247 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.3985. Min Act: -0.0000

Data Index: 496043 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.4726. Min Act: -0.0000

Data Index: 832281 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 1.9547. Min Range: -1.9547

Max Act: 1.3731. Min Act: -0.0000

Data Index: 886035 (The Pile)

Max Activating Token Index: 1008