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

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

Neuron 2916 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0626. Min Range: -1.0626

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1226227 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9873. Min Act: -0.0000

Data Index: 900311 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9810. Min Act: -0.0001

Data Index: 783455 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9581. Min Act: -0.0001

Data Index: 1317750 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1080017 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9291. Min Act: -0.0000

Data Index: 736857 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1061743 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1177675 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8771. Min Act: -0.0000

Data Index: 47106 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8791. Min Act: -0.0001

Data Index: 150675 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9180. Min Act: -0.0000

Data Index: 459352 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8842. Min Act: -0.0000

Data Index: 847588 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8798. Min Act: -0.0000

Data Index: 453229 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9000. Min Act: -0.0000

Data Index: 482543 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8757. Min Act: -0.0000

Data Index: 928813 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8699. Min Act: -0.0000

Data Index: 577843 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1158368 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8642. Min Act: -0.0000

Data Index: 880253 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1100411 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8291. Min Act: -0.0000

Data Index: 670287 (C4 (Web Text))

Max Activating Token Index: 506