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

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

Neuron 5687 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0626. Min Act: -0.0001

Data Index: 110082 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1424589 (Python Code)

Max Activating Token Index: 939

Text #2

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1630832 (Python Code)

Max Activating Token Index: 894

Text #3

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0536. Min Act: -0.0001

Data Index: 520917 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1588806 (Python Code)

Max Activating Token Index: 166

Text #5

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0516. Min Act: -0.0001

Data Index: 756488 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0539. Min Act: -0.0001

Data Index: 108053 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0519. Min Act: -0.0001

Data Index: 344372 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0489. Min Act: -0.0002

Data Index: 599625 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0469. Min Act: -0.0001

Data Index: 74583 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0603. Min Act: -0.0001

Data Index: 543978 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0455. Min Act: -0.0001

Data Index: 761161 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0505. Min Act: -0.0001

Data Index: 47806 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0434. Min Act: -0.0001

Data Index: 445075 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0448. Min Act: -0.0001

Data Index: 35210 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0460. Min Act: -0.0001

Data Index: 837463 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0509. Min Act: -0.0001

Data Index: 43667 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0367. Min Act: -0.0001

Data Index: 676050 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0445. Min Act: -0.0001

Data Index: 845946 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1614746 (Python Code)

Max Activating Token Index: 896