Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3793 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1625099 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1002072 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3547. Min Act: -0.0000

Data Index: 818048 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.4057. Min Act: -0.0000

Data Index: 965341 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1888332 (The Pile)

Max Activating Token Index: 979

Text #5

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3827. Min Act: -0.0000

Data Index: 67992 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1762768 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1207676 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1085449 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1231235 (The Pile)

Max Activating Token Index: 692

Text #10

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1041378 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1164873 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1419494 (The Pile)

Max Activating Token Index: 276

Text #13

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1493798 (The Pile)

Max Activating Token Index: 658

Text #14

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1517798 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1928076 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.3152. Min Act: -0.0000

Data Index: 102103 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1842302 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1270595 (The Pile)

Max Activating Token Index: 66

Text #19

Max Range: 0.4413. Min Range: -0.4413

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1992651 (The Pile)

Max Activating Token Index: 221