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

Dataset: The Pile

Neuron 3651 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.5077. Min Act: -0.0000

Data Index: 1218088 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.0949. Min Act: -0.0000

Data Index: 266170 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.0870. Min Act: -0.0000

Data Index: 775998 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1626853 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.0066. Min Act: -0.0000

Data Index: 1892114 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.0585. Min Act: -0.0000

Data Index: 955614 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.9997. Min Act: -0.0000

Data Index: 529905 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1103887 (The Pile)

Max Activating Token Index: 800

Text #8

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1663916 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.0498. Min Act: -0.0000

Data Index: 953281 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1692018 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.8949. Min Act: -0.0000

Data Index: 624404 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1012795 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1447116 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.9345. Min Act: -0.0000

Data Index: 15499 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.9139. Min Act: -0.0000

Data Index: 920661 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.8696. Min Act: -0.0000

Data Index: 58495 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1260342 (The Pile)

Max Activating Token Index: 472

Text #18

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1679892 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 1.5077. Min Range: -1.5077

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1490371 (The Pile)

Max Activating Token Index: 419