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

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

Neuron 1963 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: 6.2901. Min Range: -6.2901

Max Act: 6.2901. Min Act: -0.0000

Data Index: 1215884 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.8519. Min Act: -0.0000

Data Index: 1482619 (Python Code)

Max Activating Token Index: 922

Text #2

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.4069. Min Act: -0.0000

Data Index: 971984 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.6965. Min Act: -0.0000

Data Index: 1523102 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.4061. Min Act: -0.0001

Data Index: 1432695 (Python Code)

Max Activating Token Index: 279

Text #5

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.3839. Min Act: -0.0001

Data Index: 1399787 (Python Code)

Max Activating Token Index: 546

Text #6

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.1782. Min Act: -0.0000

Data Index: 592389 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.3821. Min Act: -0.0001

Data Index: 1422918 (Python Code)

Max Activating Token Index: 390

Text #8

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.3514. Min Act: -0.0000

Data Index: 1498141 (Python Code)

Max Activating Token Index: 959

Text #9

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.3133. Min Act: -0.0000

Data Index: 1551038 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.3080. Min Act: -0.0000

Data Index: 833237 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.2401. Min Act: -0.0000

Data Index: 674881 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.0394. Min Act: -0.0001

Data Index: 1411234 (Python Code)

Max Activating Token Index: 382

Text #13

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.1970. Min Act: -0.0001

Data Index: 1532807 (Python Code)

Max Activating Token Index: 389

Text #14

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.1962. Min Act: -0.0001

Data Index: 1557228 (Python Code)

Max Activating Token Index: 663

Text #15

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.2052. Min Act: -0.0001

Data Index: 1505076 (Python Code)

Max Activating Token Index: 739

Text #16

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.2093. Min Act: -0.0001

Data Index: 1444491 (Python Code)

Max Activating Token Index: 333

Text #17

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.1997. Min Act: -0.0001

Data Index: 1376989 (Python Code)

Max Activating Token Index: 495

Text #18

Max Range: 6.2901. Min Range: -6.2901

Max Act: 5.1634. Min Act: -0.0000

Data Index: 61454 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 6.2901. Min Range: -6.2901

Max Act: 4.9876. Min Act: -0.0000

Data Index: 1109692 (C4 (Web Text))

Max Activating Token Index: 1009