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

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

Neuron 4575 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0001

Data Index: 381529 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0395. Min Act: -0.0001

Data Index: 798309 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0389. Min Act: -0.0001

Data Index: 996466 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0389. Min Act: -0.0001

Data Index: 700224 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0388. Min Act: -0.0001

Data Index: 415682 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0379. Min Act: -0.0001

Data Index: 681726 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1299938 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0378. Min Act: -0.0001

Data Index: 42445 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0380. Min Act: -0.0002

Data Index: 641336 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0373. Min Act: -0.0001

Data Index: 178353 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0374. Min Act: -0.0001

Data Index: 762212 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0380. Min Act: -0.0001

Data Index: 764856 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0374. Min Act: -0.0001

Data Index: 763176 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0372. Min Act: -0.0001

Data Index: 294717 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0376. Min Act: -0.0001

Data Index: 413272 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0376. Min Act: -0.0001

Data Index: 875741 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0377. Min Act: -0.0001

Data Index: 598924 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0376. Min Act: -0.0001

Data Index: 982671 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0378. Min Act: -0.0001

Data Index: 857105 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0372. Min Act: -0.0001

Data Index: 360660 (C4 (Web Text))

Max Activating Token Index: 928