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

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

Neuron 224 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0001

Data Index: 968333 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1298012 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1068742 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0516. Min Act: -0.0001

Data Index: 577218 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0503. Min Act: -0.0001

Data Index: 881561 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1045390 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0508. Min Act: -0.0001

Data Index: 479880 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0488. Min Act: -0.0001

Data Index: 932793 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0474. Min Act: -0.0001

Data Index: 984036 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1132535 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0476. Min Act: -0.0001

Data Index: 731572 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0480. Min Act: -0.0001

Data Index: 918094 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0467. Min Act: -0.0001

Data Index: 144452 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1019091 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0460. Min Act: -0.0001

Data Index: 189147 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0430. Min Act: -0.0001

Data Index: 939669 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0453. Min Act: -0.0001

Data Index: 495265 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1180463 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0413. Min Act: -0.0001

Data Index: 502689 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1161849 (C4 (Web Text))

Max Activating Token Index: 715