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

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

Neuron 1351 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: 3.3363. Min Range: -3.3363

Max Act: 3.3363. Min Act: -0.0000

Data Index: 830014 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 3.3363. Min Range: -3.3363

Max Act: 3.0130. Min Act: -0.0000

Data Index: 452558 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.7401. Min Act: -0.0000

Data Index: 314127 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.6664. Min Act: -0.0000

Data Index: 837321 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.5427. Min Act: -0.0000

Data Index: 1285504 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.6578. Min Act: -0.0000

Data Index: 35031 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.1897. Min Act: -0.0000

Data Index: 506034 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.3264. Min Act: -0.0000

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.0599. Min Act: -0.0000

Data Index: 1194306 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.1662. Min Act: -0.0000

Data Index: 755616 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.0579. Min Act: -0.0000

Data Index: 19940 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.0758. Min Act: -0.0000

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.3075. Min Act: -0.0000

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.0789. Min Act: -0.0000

Data Index: 746187 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.1686. Min Act: -0.0000

Data Index: 884087 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.1452. Min Act: -0.0000

Data Index: 40514 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.3363. Min Range: -3.3363

Max Act: 1.7729. Min Act: -0.0000

Data Index: 705731 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 3.3363. Min Range: -3.3363

Max Act: 1.9559. Min Act: -0.0000

Data Index: 279116 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.3363. Min Range: -3.3363

Max Act: 2.0437. Min Act: -0.0000

Data Index: 694866 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 3.3363. Min Range: -3.3363

Max Act: 1.9252. Min Act: -0.0000

Data Index: 518016 (C4 (Web Text))

Max Activating Token Index: 50