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

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

Neuron 1849 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: 3.8011. Min Range: -3.8011

Max Act: 3.8011. Min Act: -0.0000

Data Index: 921533 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.1343. Min Act: -0.0000

Data Index: 649789 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.7282. Min Act: -0.0000

Data Index: 655554 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.5455. Min Act: -0.0000

Data Index: 1036066 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.6526. Min Act: -0.0000

Data Index: 481059 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.5572. Min Act: -0.0000

Data Index: 1351741 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.5289. Min Act: -0.0000

Data Index: 723026 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.4197. Min Act: -0.0000

Data Index: 696708 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.4065. Min Act: -0.0000

Data Index: 908895 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.3810. Min Act: -0.0000

Data Index: 18614 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.3369. Min Act: -0.0000

Data Index: 527004 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.4434. Min Act: -0.0000

Data Index: 604499 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.3077. Min Act: -0.0000

Data Index: 618359 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.1863. Min Act: -0.0000

Data Index: 379718 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.1764. Min Act: -0.0000

Data Index: 1560121 (Python Code)

Max Activating Token Index: 858

Text #15

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.2389. Min Act: -0.0000

Data Index: 490979 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.2453. Min Act: -0.0000

Data Index: 531063 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.2021. Min Act: -0.0000

Data Index: 1247519 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.2623. Min Act: -0.0000

Data Index: 332827 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 3.8011. Min Range: -3.8011

Max Act: 2.1504. Min Act: -0.0000

Data Index: 143259 (C4 (Web Text))

Max Activating Token Index: 208