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

Dataset: The Pile

Neuron 3514 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1674833 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0936. Min Act: 0.0000

Data Index: 740199 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0899. Min Act: 0.0000

Data Index: 695452 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0874. Min Act: 0.0000

Data Index: 858969 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1223221 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0882. Min Act: -0.0000

Data Index: 632689 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0830. Min Act: 0.0000

Data Index: 384004 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0816. Min Act: 0.0000

Data Index: 1811410 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0808. Min Act: 0.0000

Data Index: 1292641 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1169509 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1209569 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0785. Min Act: -0.0000

Data Index: 848929 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0757. Min Act: 0.0000

Data Index: 1109200 (The Pile)

Max Activating Token Index: 88

Text #13

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0784. Min Act: 0.0000

Data Index: 966594 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0779. Min Act: 0.0000

Data Index: 1218158 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0792. Min Act: -0.0000

Data Index: 896601 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0777. Min Act: -0.0000

Data Index: 676561 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0774. Min Act: 0.0000

Data Index: 781718 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0775. Min Act: 0.0000

Data Index: 421938 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1076026 (The Pile)

Max Activating Token Index: 99