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

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

Neuron 4529 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0000

Data Index: 739124 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1308202 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1015347 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0539. Min Act: -0.0000

Data Index: 194755 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0551. Min Act: -0.0000

Data Index: 162086 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0491. Min Act: -0.0000

Data Index: 156527 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0582. Min Act: -0.0000

Data Index: 948687 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0502. Min Act: -0.0000

Data Index: 254798 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0517. Min Act: -0.0000

Data Index: 492702 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0554. Min Act: -0.0000

Data Index: 190153 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0454. Min Act: -0.0000

Data Index: 791634 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0512. Min Act: -0.0000

Data Index: 749880 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1267053 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0470. Min Act: -0.0000

Data Index: 950327 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0484. Min Act: -0.0000

Data Index: 1256071 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0455. Min Act: -0.0000

Data Index: 907188 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0511. Min Act: -0.0000

Data Index: 650481 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0478. Min Act: -0.0000

Data Index: 626157 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0508. Min Act: -0.0000

Data Index: 916813 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0491. Min Act: -0.0000

Data Index: 85709 (C4 (Web Text))

Max Activating Token Index: 71