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

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

Neuron 1417 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: 2.3594. Min Range: -2.3594

Max Act: 2.3594. Min Act: -0.0000

Data Index: 559461 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 2.3594. Min Range: -2.3594

Max Act: 2.2317. Min Act: -0.0000

Data Index: 510855 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1292639 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 2.3594. Min Range: -2.3594

Max Act: 2.0054. Min Act: -0.0000

Data Index: 470393 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.8794. Min Act: -0.0000

Data Index: 694529 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.7798. Min Act: -0.0000

Data Index: 1309929 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.7241. Min Act: -0.0000

Data Index: 199137 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.8221. Min Act: -0.0000

Data Index: 1129264 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.8530. Min Act: -0.0000

Data Index: 862690 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.7151. Min Act: -0.0000

Data Index: 1040356 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.7964. Min Act: -0.0000

Data Index: 198903 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.6764. Min Act: -0.0000

Data Index: 434258 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1239565 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.6471. Min Act: -0.0000

Data Index: 1035324 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.6180. Min Act: -0.0000

Data Index: 1041243 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1330965 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.5345. Min Act: -0.0000

Data Index: 1317819 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.5691. Min Act: -0.0000

Data Index: 1276587 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.5586. Min Act: -0.0000

Data Index: 609937 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 2.3594. Min Range: -2.3594

Max Act: 1.3853. Min Act: -0.0000

Data Index: 384113 (C4 (Web Text))

Max Activating Token Index: 994