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

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

Neuron 2095 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.8798. Min Act: -0.0003

Data Index: 694923 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.8293. Min Act: -0.0003

Data Index: 820634 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.7898. Min Act: -0.0003

Data Index: 1056204 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.6513. Min Act: -0.0003

Data Index: 1313793 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.5498. Min Act: -0.0002

Data Index: 1280103 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.4036. Min Act: -0.0003

Data Index: 480792 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.3801. Min Act: -0.0003

Data Index: 360661 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.3258. Min Act: -0.0003

Data Index: 1188612 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.2773. Min Act: -0.0003

Data Index: 610699 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.2453. Min Act: -0.0003

Data Index: 1078493 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.2078. Min Act: -0.0003

Data Index: 240268 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.2381. Min Act: -0.0003

Data Index: 156497 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.1527. Min Act: -0.0003

Data Index: 914375 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.1750. Min Act: -0.0003

Data Index: 940215 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.1585. Min Act: -0.0003

Data Index: 761312 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.1106. Min Act: -0.0003

Data Index: 272316 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.0151. Min Act: -0.0003

Data Index: 1092470 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 1.8798. Min Range: -1.8798

Max Act: 0.9748. Min Act: -0.0003

Data Index: 805629 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 1.8798. Min Range: -1.8798

Max Act: 0.9682. Min Act: -0.0003

Data Index: 1219914 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.8798. Min Range: -1.8798

Max Act: 0.9358. Min Act: -0.0003

Data Index: 394082 (C4 (Web Text))

Max Activating Token Index: 415