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

Dataset: The Pile

Neuron 3847 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: 1.4018. Min Range: -1.4018

Max Act: 1.4018. Min Act: -0.0000

Data Index: 1340934 (The Pile)

Max Activating Token Index: 889

Text #1

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.2706. Min Act: -0.0000

Data Index: 621125 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.1346. Min Act: -0.0000

Data Index: 40901 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.1849. Min Act: -0.0000

Data Index: 1995698 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1022407 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1159536 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.0916. Min Act: -0.0000

Data Index: 165818 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.0016. Min Act: -0.0000

Data Index: 987412 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 1.4018. Min Range: -1.4018

Max Act: 0.9990. Min Act: 0.0000

Data Index: 287044 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 1.4018. Min Range: -1.4018

Max Act: 0.9560. Min Act: -0.0000

Data Index: 651452 (The Pile)

Max Activating Token Index: 29

Text #10

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.0310. Min Act: -0.0000

Data Index: 949033 (The Pile)

Max Activating Token Index: 314

Text #11

Max Range: 1.4018. Min Range: -1.4018

Max Act: 0.9707. Min Act: -0.0000

Data Index: 322226 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1800204 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 1.4018. Min Range: -1.4018

Max Act: 0.9652. Min Act: -0.0000

Data Index: 961773 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 1.4018. Min Range: -1.4018

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1054487 (The Pile)

Max Activating Token Index: 85

Text #15

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.0424. Min Act: -0.0000

Data Index: 1604539 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.0376. Min Act: -0.0000

Data Index: 132584 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 1.4018. Min Range: -1.4018

Max Act: 0.9657. Min Act: -0.0000

Data Index: 698754 (The Pile)

Max Activating Token Index: 893

Text #18

Max Range: 1.4018. Min Range: -1.4018

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1422891 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 1.4018. Min Range: -1.4018

Max Act: 1.0225. Min Act: -0.0000

Data Index: 504878 (The Pile)

Max Activating Token Index: 264