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

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

Neuron 657 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0004

Data Index: 264455 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0456. Min Act: -0.0004

Data Index: 72514 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0463. Min Act: -0.0004

Data Index: 1054558 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0419. Min Act: -0.0004

Data Index: 1269615 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0408. Min Act: -0.0004

Data Index: 806254 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0403. Min Act: -0.0004

Data Index: 1324557 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0403. Min Act: -0.0004

Data Index: 1265520 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0392. Min Act: -0.0004

Data Index: 999292 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0392. Min Act: -0.0004

Data Index: 585679 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0380. Min Act: -0.0004

Data Index: 463650 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0387. Min Act: -0.0004

Data Index: 989396 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0383. Min Act: -0.0004

Data Index: 693596 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0372. Min Act: -0.0004

Data Index: 894732 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0388. Min Act: -0.0004

Data Index: 463112 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0386. Min Act: -0.0004

Data Index: 1350488 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0378. Min Act: -0.0004

Data Index: 917906 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0366. Min Act: -0.0004

Data Index: 638325 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0373. Min Act: -0.0004

Data Index: 1205676 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0372. Min Act: -0.0004

Data Index: 685831 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0371. Min Act: -0.0004

Data Index: 767656 (C4 (Web Text))

Max Activating Token Index: 710