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

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

Neuron 2748 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.9236. Min Act: -0.0001

Data Index: 658339 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7561. Min Act: -0.0001

Data Index: 160932 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8191. Min Act: -0.0001

Data Index: 221306 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7387. Min Act: -0.0001

Data Index: 19664 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7308. Min Act: -0.0001

Data Index: 1063752 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7027. Min Act: -0.0001

Data Index: 775949 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6288. Min Act: -0.0001

Data Index: 745007 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6658. Min Act: -0.0001

Data Index: 609203 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5627. Min Act: -0.0001

Data Index: 878859 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6108. Min Act: -0.0001

Data Index: 726529 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5767. Min Act: -0.0001

Data Index: 1291719 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5779. Min Act: -0.0001

Data Index: 1088425 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5464. Min Act: -0.0001

Data Index: 89613 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5016. Min Act: -0.0001

Data Index: 378214 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5807. Min Act: -0.0001

Data Index: 823301 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5792. Min Act: -0.0001

Data Index: 138860 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5182. Min Act: -0.0001

Data Index: 1139465 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5624. Min Act: -0.0001

Data Index: 651409 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5425. Min Act: -0.0001

Data Index: 689960 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5306. Min Act: -0.0001

Data Index: 1318706 (C4 (Web Text))

Max Activating Token Index: 700