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

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

Neuron 2986 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1423. Min Range: -4.1423

Max Act: 4.1423. Min Act: -0.0000

Data Index: 619752 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 4.1423. Min Range: -4.1423

Max Act: 3.5512. Min Act: -0.0000

Data Index: 510287 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 4.1423. Min Range: -4.1423

Max Act: 3.6504. Min Act: -0.0000

Data Index: 1080150 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 4.1423. Min Range: -4.1423

Max Act: 3.4714. Min Act: -0.0000

Data Index: 1046728 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 4.1423. Min Range: -4.1423

Max Act: 3.2694. Min Act: -0.0000

Data Index: 478036 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 4.1423. Min Range: -4.1423

Max Act: 3.0718. Min Act: -0.0000

Data Index: 590748 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 4.1423. Min Range: -4.1423

Max Act: 3.1825. Min Act: -0.0000

Data Index: 432480 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 4.1423. Min Range: -4.1423

Max Act: 3.1677. Min Act: -0.0000

Data Index: 1053575 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.9552. Min Act: -0.0000

Data Index: 315241 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.8455. Min Act: -0.0000

Data Index: 213560 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.9771. Min Act: -0.0000

Data Index: 1356130 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.7887. Min Act: -0.0000

Data Index: 527052 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.8701. Min Act: -0.0000

Data Index: 1323065 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.8838. Min Act: -0.0000

Data Index: 309651 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.8642. Min Act: -0.0000

Data Index: 814131 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.8594. Min Act: -0.0000

Data Index: 1062257 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.8500. Min Act: -0.0000

Data Index: 1173140 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.6454. Min Act: -0.0000

Data Index: 677120 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.6564. Min Act: -0.0000

Data Index: 695422 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 4.1423. Min Range: -4.1423

Max Act: 2.7804. Min Act: -0.0000

Data Index: 1241581 (C4 (Web Text))

Max Activating Token Index: 1015