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

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

Neuron 4629 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: 0.3108. Min Range: -0.3108

Max Act: 0.3108. Min Act: -0.0000

Data Index: 1366801 (Python Code)

Max Activating Token Index: 712

Text #1

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1623498 (Python Code)

Max Activating Token Index: 368

Text #2

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1542083 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2184. Min Act: -0.0000

Data Index: 201705 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1282779 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1883. Min Act: -0.0000

Data Index: 585001 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1816. Min Act: -0.0000

Data Index: 45346 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1757. Min Act: -0.0000

Data Index: 954087 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1782. Min Act: -0.0000

Data Index: 123030 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1460871 (Python Code)

Max Activating Token Index: 621

Text #10

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1392696 (Python Code)

Max Activating Token Index: 899

Text #11

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1706. Min Act: -0.0000

Data Index: 975904 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1854. Min Act: -0.0000

Data Index: 824327 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1831. Min Act: -0.0000

Data Index: 282340 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1765. Min Act: -0.0000

Data Index: 788521 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1661. Min Act: -0.0000

Data Index: 798960 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1448343 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1454344 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1451750 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 0.3108. Min Range: -0.3108

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1595941 (Python Code)

Max Activating Token Index: 488