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

Dataset: The Pile

Neuron 3613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7777. Min Act: -0.0000

Data Index: 504470 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.9650. Min Act: -0.0000

Data Index: 1177347 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.8367. Min Act: -0.0000

Data Index: 178079 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6199. Min Act: -0.0000

Data Index: 748070 (The Pile)

Max Activating Token Index: 884

Text #4

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6997. Min Act: -0.0000

Data Index: 912131 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.8646. Min Act: -0.0000

Data Index: 414810 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6787. Min Act: -0.0000

Data Index: 1612929 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.5938. Min Act: -0.0000

Data Index: 811216 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7979. Min Act: -0.0000

Data Index: 7513 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.6482. Min Act: -0.0000

Data Index: 1050231 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7361. Min Act: -0.0000

Data Index: 1034566 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.5906. Min Act: -0.0000

Data Index: 957519 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.5547. Min Act: -0.0000

Data Index: 425246 (The Pile)

Max Activating Token Index: 583

Text #13

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7102. Min Act: -0.0000

Data Index: 1909240 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1539425 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.3550. Min Act: -0.0000

Data Index: 229052 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.5934. Min Act: -0.0000

Data Index: 430467 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1979269 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.5463. Min Act: -0.0000

Data Index: 1190025 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 1.9650. Min Range: -1.9650

Max Act: 1.5882. Min Act: -0.0000

Data Index: 151772 (The Pile)

Max Activating Token Index: 496