Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1347 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0005

Data Index: 42687 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0884. Min Act: -0.0005

Data Index: 449638 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0812. Min Act: -0.0005

Data Index: 384762 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0863. Min Act: -0.0005

Data Index: 830462 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0839. Min Act: -0.0005

Data Index: 1192671 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0764. Min Act: -0.0005

Data Index: 920611 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0708. Min Act: -0.0005

Data Index: 1308373 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0800. Min Act: -0.0005

Data Index: 436752 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0748. Min Act: -0.0005

Data Index: 459900 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0779. Min Act: -0.0005

Data Index: 190400 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0793. Min Act: -0.0005

Data Index: 346978 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0767. Min Act: -0.0005

Data Index: 670031 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0793. Min Act: -0.0005

Data Index: 966566 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0758. Min Act: -0.0005

Data Index: 501730 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0696. Min Act: -0.0005

Data Index: 438993 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0764. Min Act: -0.0005

Data Index: 876578 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0740. Min Act: -0.0005

Data Index: 1351335 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0725. Min Act: -0.0005

Data Index: 591103 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0712. Min Act: -0.0005

Data Index: 405350 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0709. Min Act: -0.0005

Data Index: 1180567 (C4 (Web Text))

Max Activating Token Index: 557