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

Dataset: The Pile

Neuron 4560 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: 1.0804. Min Range: -1.0804

Max Act: 1.0804. Min Act: -0.0000

Data Index: 827293 (The Pile)

Max Activating Token Index: 764

Text #1

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1172469 (The Pile)

Max Activating Token Index: 34

Text #2

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7934. Min Act: -0.0000

Data Index: 439934 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1887767 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7990. Min Act: -0.0000

Data Index: 738863 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1414238 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7915. Min Act: 0.0000

Data Index: 976059 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.8129. Min Act: 0.0000

Data Index: 477783 (The Pile)

Max Activating Token Index: 275

Text #8

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1064994 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1513902 (The Pile)

Max Activating Token Index: 834

Text #10

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7440. Min Act: 0.0000

Data Index: 314511 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7311. Min Act: -0.0000

Data Index: 435285 (The Pile)

Max Activating Token Index: 771

Text #12

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7196. Min Act: -0.0000

Data Index: 347078 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1956530 (The Pile)

Max Activating Token Index: 343

Text #14

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.6793. Min Act: 0.0000

Data Index: 205097 (The Pile)

Max Activating Token Index: 423

Text #15

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1626432 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.6908. Min Act: -0.0000

Data Index: 360314 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1587412 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1809542 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1100624 (The Pile)

Max Activating Token Index: 219