Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1818 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0908. Min Range: -2.0908

Max Act: 2.0908. Min Act: -0.0000

Data Index: 742210 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.9230. Min Act: -0.0001

Data Index: 1138306 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.9064. Min Act: -0.0000

Data Index: 627264 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.9009. Min Act: -0.0001

Data Index: 1165129 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 2.0908. Min Range: -2.0908

Max Act: 2.0209. Min Act: -0.0001

Data Index: 385131 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.8889. Min Act: -0.0001

Data Index: 601834 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.9679. Min Act: -0.0000

Data Index: 947026 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.8071. Min Act: -0.0000

Data Index: 4288 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.7870. Min Act: -0.0000

Data Index: 931188 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.9338. Min Act: -0.0000

Data Index: 1183033 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.6622. Min Act: -0.0001

Data Index: 1226990 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.8558. Min Act: -0.0000

Data Index: 553831 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.6466. Min Act: -0.0000

Data Index: 308921 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.6657. Min Act: -0.0000

Data Index: 361820 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.7270. Min Act: -0.0000

Data Index: 414374 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.8015. Min Act: -0.0000

Data Index: 486921 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.7114. Min Act: -0.0000

Data Index: 1130826 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1075765 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.6880. Min Act: -0.0000

Data Index: 190801 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 2.0908. Min Range: -2.0908

Max Act: 1.7635. Min Act: -0.0000

Data Index: 509405 (C4 (Web Text))

Max Activating Token Index: 541