Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2674 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0419. Min Act: -0.0003

Data Index: 378841 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1152148 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1875 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0373. Min Act: -0.0002

Data Index: 178854 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0376. Min Act: -0.0003

Data Index: 628011 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0381. Min Act: -0.0003

Data Index: 901628 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0374. Min Act: -0.0002

Data Index: 170841 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0363. Min Act: -0.0003

Data Index: 758768 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0373. Min Act: -0.0003

Data Index: 834164 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0365. Min Act: -0.0003

Data Index: 34152 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1158735 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0375. Min Act: -0.0003

Data Index: 937542 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0368. Min Act: -0.0003

Data Index: 422792 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0368. Min Act: -0.0003

Data Index: 424737 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0351. Min Act: -0.0003

Data Index: 474241 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0366. Min Act: -0.0003

Data Index: 404476 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0374. Min Act: -0.0003

Data Index: 617596 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0353. Min Act: -0.0003

Data Index: 178299 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1285894 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0368. Min Act: -0.0003

Data Index: 839935 (C4 (Web Text))

Max Activating Token Index: 518