Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1628 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0553. Min Act: -0.0000

Data Index: 908654 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0001

Data Index: 823461 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0488. Min Act: -0.0001

Data Index: 589602 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0493. Min Act: -0.0001

Data Index: 134610 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0454. Min Act: -0.0001

Data Index: 316564 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0465. Min Act: -0.0001

Data Index: 342427 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0437. Min Act: -0.0001

Data Index: 831964 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0440. Min Act: -0.0001

Data Index: 53613 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0465. Min Act: -0.0001

Data Index: 986189 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1226773 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0430. Min Act: -0.0000

Data Index: 1198837 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0422. Min Act: -0.0001

Data Index: 110165 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0420. Min Act: -0.0001

Data Index: 1308647 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0410. Min Act: 0.0000

Data Index: 62509 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0435. Min Act: -0.0001

Data Index: 268631 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0432. Min Act: -0.0000

Data Index: 277478 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0397. Min Act: -0.0001

Data Index: 702452 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0407. Min Act: -0.0001

Data Index: 730309 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0403. Min Act: -0.0001

Data Index: 539736 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0395. Min Act: -0.0001

Data Index: 916577 (C4 (Web Text))

Max Activating Token Index: 8