Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1855 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0625. Min Act: -0.0001

Data Index: 460528 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1314998 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0640. Min Act: -0.0001

Data Index: 283108 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1185862 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0646. Min Act: -0.0001

Data Index: 40043 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1251956 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1072168 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0615. Min Act: -0.0001

Data Index: 689388 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0621. Min Act: -0.0001

Data Index: 926455 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1090836 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0623. Min Act: -0.0001

Data Index: 803526 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0637. Min Act: -0.0001

Data Index: 642503 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0608. Min Act: -0.0001

Data Index: 719325 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0571. Min Act: -0.0001

Data Index: 879992 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0559. Min Act: -0.0001

Data Index: 777369 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1195550 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0573. Min Act: -0.0001

Data Index: 518552 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1415047 (Python Code)

Max Activating Token Index: 953

Text #18

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0635. Min Act: -0.0001

Data Index: 949347 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0557. Min Act: -0.0001

Data Index: 518237 (C4 (Web Text))

Max Activating Token Index: 878