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

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

Neuron 2493 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.9067. Min Act: -0.0001

Data Index: 585868 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.8059. Min Act: -0.0000

Data Index: 174829 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.8217. Min Act: -0.0001

Data Index: 973829 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7483. Min Act: -0.0000

Data Index: 82963 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6926. Min Act: -0.0001

Data Index: 1013364 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7351. Min Act: -0.0001

Data Index: 616935 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7017. Min Act: -0.0001

Data Index: 1192925 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6998. Min Act: -0.0001

Data Index: 744399 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7380. Min Act: -0.0001

Data Index: 20452 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7361. Min Act: -0.0001

Data Index: 346304 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6750. Min Act: -0.0001

Data Index: 642192 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6907. Min Act: -0.0000

Data Index: 477073 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6667. Min Act: -0.0001

Data Index: 468850 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7095. Min Act: -0.0001

Data Index: 447775 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1197450 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6571. Min Act: -0.0001

Data Index: 981613 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5988. Min Act: -0.0000

Data Index: 201932 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6443. Min Act: -0.0001

Data Index: 750494 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1271954 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.9067. Min Range: -0.9067

Max Act: 0.5989. Min Act: -0.0001

Data Index: 2499 (C4 (Web Text))

Max Activating Token Index: 729