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

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

Neuron 2306 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.6804. Min Act: -0.0000

Data Index: 592863 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.6342. Min Act: -0.0000

Data Index: 233704 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1231614 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5753. Min Act: -0.0000

Data Index: 485330 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5238. Min Act: -0.0000

Data Index: 74012 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.6364. Min Act: -0.0000

Data Index: 37906 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5100. Min Act: -0.0000

Data Index: 124797 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4780. Min Act: -0.0000

Data Index: 145567 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1063096 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5316. Min Act: -0.0000

Data Index: 604009 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5068. Min Act: -0.0000

Data Index: 685742 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4380. Min Act: -0.0000

Data Index: 484343 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1287305 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4127. Min Act: -0.0000

Data Index: 126885 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4429. Min Act: -0.0000

Data Index: 535298 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1255701 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1080763 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1270953 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.4183. Min Act: -0.0000

Data Index: 491174 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.3944. Min Act: -0.0000

Data Index: 660379 (C4 (Web Text))

Max Activating Token Index: 815