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

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

Neuron 4647 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: 1.1619. Min Range: -1.1619

Max Act: 1.1045. Min Act: -0.0000

Data Index: 669689 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0547. Min Act: -0.0000

Data Index: 743045 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1325842 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0286. Min Act: -0.0000

Data Index: 630919 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.1619. Min Act: -0.0000

Data Index: 692723 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0977. Min Act: -0.0000

Data Index: 502341 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0463. Min Act: -0.0000

Data Index: 901137 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0525. Min Act: -0.0000

Data Index: 273970 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0182. Min Act: -0.0000

Data Index: 979559 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1022075 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1102998 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0519. Min Act: -0.0000

Data Index: 923160 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9374. Min Act: -0.0000

Data Index: 730525 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9535. Min Act: -0.0000

Data Index: 87491 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0124. Min Act: -0.0000

Data Index: 322651 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9845. Min Act: -0.0000

Data Index: 388922 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0026. Min Act: -0.0000

Data Index: 344174 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9596. Min Act: -0.0000

Data Index: 319326 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9913. Min Act: -0.0000

Data Index: 670011 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1144413 (C4 (Web Text))

Max Activating Token Index: 342