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

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

Neuron 613 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5594. Min Act: -0.0001

Data Index: 1560659 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5739. Min Act: -0.0001

Data Index: 1507507 (Python Code)

Max Activating Token Index: 685

Text #2

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5487. Min Act: -0.0001

Data Index: 1645358 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1480083 (Python Code)

Max Activating Token Index: 277

Text #4

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1633281 (Python Code)

Max Activating Token Index: 656

Text #5

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5082. Min Act: -0.0001

Data Index: 1484586 (Python Code)

Max Activating Token Index: 655

Text #6

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1544493 (Python Code)

Max Activating Token Index: 477

Text #7

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1141674 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1551113 (Python Code)

Max Activating Token Index: 277

Text #9

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4670. Min Act: -0.0001

Data Index: 1392971 (Python Code)

Max Activating Token Index: 626

Text #10

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1575067 (Python Code)

Max Activating Token Index: 500

Text #11

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4670. Min Act: -0.0001

Data Index: 1610903 (Python Code)

Max Activating Token Index: 401

Text #12

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1478590 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4783. Min Act: -0.0000

Data Index: 278617 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1425479 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4719. Min Act: -0.0001

Data Index: 1647406 (Python Code)

Max Activating Token Index: 369

Text #16

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1426559 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1317576 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4761. Min Act: -0.0001

Data Index: 1449321 (Python Code)

Max Activating Token Index: 895

Text #19

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1592150 (Python Code)

Max Activating Token Index: 384