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

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

Neuron 1788 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0245. Min Range: -1.0245

Max Act: 1.0245. Min Act: -0.0000

Data Index: 198950 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.9327. Min Act: -0.0000

Data Index: 593615 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.9331. Min Act: -0.0000

Data Index: 102747 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.9264. Min Act: -0.0000

Data Index: 113815 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.9215. Min Act: -0.0000

Data Index: 91516 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8973. Min Act: -0.0000

Data Index: 437472 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1109598 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8873. Min Act: -0.0000

Data Index: 552777 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8636. Min Act: -0.0000

Data Index: 465031 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8843. Min Act: -0.0000

Data Index: 309137 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8588. Min Act: -0.0000

Data Index: 156635 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1482816 (Python Code)

Max Activating Token Index: 946

Text #12

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8816. Min Act: -0.0000

Data Index: 74221 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8404. Min Act: -0.0000

Data Index: 623079 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8977. Min Act: -0.0000

Data Index: 252355 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8418. Min Act: -0.0000

Data Index: 503658 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8694. Min Act: -0.0000

Data Index: 188535 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1123121 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8666. Min Act: -0.0000

Data Index: 685807 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1003593 (C4 (Web Text))

Max Activating Token Index: 649