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

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

Neuron 4630 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: 4.6698. Min Range: -4.6698

Max Act: 4.6698. Min Act: -0.0000

Data Index: 521407 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 4.6698. Min Range: -4.6698

Max Act: 4.1048. Min Act: -0.0000

Data Index: 963528 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 4.6698. Min Range: -4.6698

Max Act: 4.0590. Min Act: -0.0000

Data Index: 1124127 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.9578. Min Act: -0.0000

Data Index: 1011526 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.7384. Min Act: -0.0000

Data Index: 724536 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.6550. Min Act: -0.0000

Data Index: 519111 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.4984. Min Act: -0.0000

Data Index: 774549 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.4490. Min Act: -0.0000

Data Index: 759911 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.5788. Min Act: -0.0000

Data Index: 742563 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.7161. Min Act: -0.0000

Data Index: 816992 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.3730. Min Act: -0.0000

Data Index: 507281 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.6737. Min Act: -0.0000

Data Index: 917085 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.5010. Min Act: -0.0000

Data Index: 521484 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.4923. Min Act: -0.0000

Data Index: 205559 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.4390. Min Act: -0.0000

Data Index: 279701 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.5734. Min Act: -0.0000

Data Index: 1111824 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.5603. Min Act: -0.0000

Data Index: 752693 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.2529. Min Act: -0.0000

Data Index: 440612 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.2317. Min Act: -0.0000

Data Index: 901375 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 4.6698. Min Range: -4.6698

Max Act: 3.2100. Min Act: -0.0000

Data Index: 1118733 (C4 (Web Text))

Max Activating Token Index: 451