Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1506 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0003

Data Index: 104209 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0443. Min Act: -0.0003

Data Index: 481720 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1249989 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0433. Min Act: -0.0003

Data Index: 913087 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0424. Min Act: -0.0003

Data Index: 554390 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1064680 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0415. Min Act: -0.0003

Data Index: 502041 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0405. Min Act: -0.0003

Data Index: 964217 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0406. Min Act: -0.0003

Data Index: 629876 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0405. Min Act: -0.0003

Data Index: 603690 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1035713 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0400. Min Act: -0.0003

Data Index: 531451 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0409. Min Act: -0.0004

Data Index: 816184 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0398. Min Act: -0.0003

Data Index: 538715 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0394. Min Act: -0.0003

Data Index: 594983 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0386. Min Act: -0.0003

Data Index: 343753 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0401. Min Act: -0.0004

Data Index: 344026 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0377. Min Act: -0.0003

Data Index: 384329 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1140329 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0389. Min Act: -0.0003

Data Index: 892962 (C4 (Web Text))

Max Activating Token Index: 367