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

Dataset: The Pile

Neuron 2377 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0328. Min Range: -1.0328

Max Act: 1.0046. Min Act: -0.0000

Data Index: 856362 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 1.0328. Min Range: -1.0328

Max Act: 1.0328. Min Act: -0.0000

Data Index: 738174 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1601744 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1382640 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1450555 (The Pile)

Max Activating Token Index: 503

Text #5

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.9090. Min Act: -0.0000

Data Index: 611537 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.9370. Min Act: -0.0000

Data Index: 929190 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1233896 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1926739 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1856012 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8847. Min Act: -0.0000

Data Index: 154164 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7102. Min Act: -0.0000

Data Index: 492543 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1409936 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1452853 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8564. Min Act: -0.0000

Data Index: 742152 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7906. Min Act: -0.0000

Data Index: 410892 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7617. Min Act: -0.0000

Data Index: 933031 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8046. Min Act: -0.0000

Data Index: 239809 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1651511 (The Pile)

Max Activating Token Index: 2

Text #19

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1890669 (The Pile)

Max Activating Token Index: 682