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

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

Neuron 1661 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3863. Min Range: -3.3863

Max Act: 3.0827. Min Act: -0.0000

Data Index: 1098848 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 3.3863. Min Range: -3.3863

Max Act: 3.3863. Min Act: -0.0000

Data Index: 110008 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 3.3863. Min Range: -3.3863

Max Act: 3.1066. Min Act: -0.0000

Data Index: 486867 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.9307. Min Act: -0.0000

Data Index: 21866 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.6527. Min Act: -0.0000

Data Index: 1044847 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.7908. Min Act: -0.0000

Data Index: 965548 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.8728. Min Act: -0.0000

Data Index: 741966 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.8391. Min Act: -0.0000

Data Index: 1013785 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.7822. Min Act: -0.0000

Data Index: 999423 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.6482. Min Act: -0.0000

Data Index: 673669 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.7779. Min Act: -0.0000

Data Index: 373270 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.6366. Min Act: -0.0000

Data Index: 866329 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.7593. Min Act: -0.0000

Data Index: 64287 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.5525. Min Act: -0.0000

Data Index: 570146 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.6847. Min Act: -0.0000

Data Index: 889116 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.6707. Min Act: -0.0000

Data Index: 167365 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.6533. Min Act: -0.0000

Data Index: 734694 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.6598. Min Act: -0.0000

Data Index: 889135 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.6492. Min Act: -0.0000

Data Index: 502792 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 3.3863. Min Range: -3.3863

Max Act: 2.4937. Min Act: -0.0000

Data Index: 1278656 (C4 (Web Text))

Max Activating Token Index: 468