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

Dataset: The Pile

Neuron 3477 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1268475 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1240777 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4790. Min Act: -0.0000

Data Index: 87494 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4638. Min Act: -0.0000

Data Index: 961939 (The Pile)

Max Activating Token Index: 506

Text #4

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1630397 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1855355 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4381. Min Act: -0.0000

Data Index: 934952 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1153494 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4432. Min Act: -0.0000

Data Index: 512751 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3743. Min Act: -0.0000

Data Index: 658835 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3976. Min Act: -0.0000

Data Index: 230214 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1504079 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3916. Min Act: -0.0000

Data Index: 562560 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1119843 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3770. Min Act: -0.0000

Data Index: 516726 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1364305 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1279823 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3688. Min Act: -0.0000

Data Index: 4729 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1891689 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1046841 (The Pile)

Max Activating Token Index: 633