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

Dataset: The Pile

Neuron 609 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: 1.7629. Min Range: -1.7629

Max Act: 1.7629. Min Act: -0.0000

Data Index: 1624222 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1134942 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.4147. Min Act: -0.0000

Data Index: 1585193 (The Pile)

Max Activating Token Index: 616

Text #3

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.3226. Min Act: -0.0000

Data Index: 593263 (The Pile)

Max Activating Token Index: 605

Text #4

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1726467 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1055774 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1550223 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 1.7629. Min Range: -1.7629

Max Act: 0.9056. Min Act: -0.0000

Data Index: 418998 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.1670. Min Act: -0.0000

Data Index: 771197 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.0788. Min Act: -0.0000

Data Index: 433450 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.0863. Min Act: -0.0000

Data Index: 550091 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.0655. Min Act: -0.0000

Data Index: 309298 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 1.7629. Min Range: -1.7629

Max Act: 0.9875. Min Act: -0.0000

Data Index: 78542 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.0931. Min Act: -0.0000

Data Index: 210039 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.0070. Min Act: -0.0000

Data Index: 224018 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.0842. Min Act: -0.0000

Data Index: 608527 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.0121. Min Act: -0.0000

Data Index: 904250 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.0229. Min Act: -0.0000

Data Index: 581653 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.1885. Min Act: -0.0000

Data Index: 1752528 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 1.7629. Min Range: -1.7629

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1561569 (The Pile)

Max Activating Token Index: 816