Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1328 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8031. Min Range: -4.8031

Max Act: 4.8031. Min Act: -0.0000

Data Index: 753388 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 4.8031. Min Range: -4.8031

Max Act: 4.0670. Min Act: -0.0000

Data Index: 249720 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 4.8031. Min Range: -4.8031

Max Act: 4.1072. Min Act: -0.0000

Data Index: 644189 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.6649. Min Act: -0.0000

Data Index: 934617 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.5369. Min Act: -0.0000

Data Index: 126897 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.3617. Min Act: -0.0000

Data Index: 1159739 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 4.8031. Min Range: -4.8031

Max Act: 2.9358. Min Act: -0.0000

Data Index: 1190866 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.4040. Min Act: -0.0000

Data Index: 48081 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.4392. Min Act: -0.0000

Data Index: 1076252 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.0385. Min Act: -0.0000

Data Index: 926843 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.5012. Min Act: -0.0000

Data Index: 666844 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.3041. Min Act: -0.0000

Data Index: 825541 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 4.8031. Min Range: -4.8031

Max Act: 2.7861. Min Act: -0.0000

Data Index: 839626 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 4.8031. Min Range: -4.8031

Max Act: 2.8529. Min Act: -0.0000

Data Index: 1110766 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 4.8031. Min Range: -4.8031

Max Act: 2.9434. Min Act: -0.0000

Data Index: 400513 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.3492. Min Act: -0.0000

Data Index: 219431 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 4.8031. Min Range: -4.8031

Max Act: 2.8500. Min Act: -0.0000

Data Index: 586544 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 4.8031. Min Range: -4.8031

Max Act: 3.0118. Min Act: -0.0001

Data Index: 230786 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 4.8031. Min Range: -4.8031

Max Act: 2.8829. Min Act: -0.0000

Data Index: 578849 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 4.8031. Min Range: -4.8031

Max Act: 2.5952. Min Act: -0.0000

Data Index: 234340 (C4 (Web Text))

Max Activating Token Index: 700