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

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

Neuron 2082 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.5274. Min Act: -0.0003

Data Index: 655562 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4395. Min Act: -0.0004

Data Index: 715288 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4122. Min Act: -0.0003

Data Index: 1069047 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4387. Min Act: -0.0003

Data Index: 460935 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4853. Min Act: -0.0003

Data Index: 949812 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4559. Min Act: -0.0003

Data Index: 16009 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.3979. Min Act: -0.0003

Data Index: 385284 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4448. Min Act: -0.0004

Data Index: 966676 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.5001. Min Act: -0.0003

Data Index: 489266 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.5007. Min Act: -0.0003

Data Index: 796741 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4659. Min Act: -0.0003

Data Index: 610563 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4658. Min Act: -0.0003

Data Index: 200211 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4826. Min Act: -0.0003

Data Index: 951390 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4366. Min Act: -0.0003

Data Index: 526962 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4758. Min Act: -0.0003

Data Index: 598314 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4439. Min Act: -0.0003

Data Index: 753216 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4172. Min Act: -0.0003

Data Index: 891860 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4571. Min Act: -0.0003

Data Index: 642657 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.4840. Min Act: -0.0003

Data Index: 1166383 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.5274. Min Range: -0.5274

Max Act: 0.5024. Min Act: -0.0003

Data Index: 306434 (C4 (Web Text))

Max Activating Token Index: 104