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

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

Neuron 1505 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1092908 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0500. Min Act: -0.0000

Data Index: 378942 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0481. Min Act: -0.0000

Data Index: 648857 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0468. Min Act: -0.0000

Data Index: 91776 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0443. Min Act: -0.0000

Data Index: 250668 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1108676 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0403. Min Act: -0.0000

Data Index: 951495 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0395. Min Act: -0.0000

Data Index: 94026 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1131720 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1135908 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0395. Min Act: -0.0000

Data Index: 917479 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0404. Min Act: -0.0000

Data Index: 884874 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0414. Min Act: -0.0000

Data Index: 365666 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0387. Min Act: -0.0000

Data Index: 777616 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0385. Min Act: -0.0000

Data Index: 472891 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0354. Min Act: -0.0000

Data Index: 1345780 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0395. Min Act: -0.0000

Data Index: 491961 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0378. Min Act: -0.0000

Data Index: 351788 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1291040 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0375. Min Act: -0.0000

Data Index: 606046 (C4 (Web Text))

Max Activating Token Index: 70