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

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

Neuron 1280 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0661. Min Act: -0.0001

Data Index: 754161 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1318740 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0418. Min Act: -0.0001

Data Index: 210931 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0460. Min Act: -0.0002

Data Index: 361559 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1308136 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0416. Min Act: -0.0002

Data Index: 42894 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0403. Min Act: -0.0002

Data Index: 154602 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0394. Min Act: -0.0001

Data Index: 937174 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1037065 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0371. Min Act: -0.0002

Data Index: 302778 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1104122 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0419. Min Act: -0.0001

Data Index: 175303 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1012002 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0396. Min Act: -0.0001

Data Index: 807629 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1254473 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0401. Min Act: -0.0001

Data Index: 320299 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0388. Min Act: -0.0002

Data Index: 674158 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0396. Min Act: -0.0001

Data Index: 106485 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0366. Min Act: -0.0002

Data Index: 499523 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0339. Min Act: -0.0001

Data Index: 711647 (C4 (Web Text))

Max Activating Token Index: 918