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

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

Neuron 3523 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0000

Data Index: 443398 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0832. Min Act: -0.0001

Data Index: 130936 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0819. Min Act: -0.0001

Data Index: 146346 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0735. Min Act: -0.0001

Data Index: 88403 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0734. Min Act: -0.0001

Data Index: 151713 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0551. Min Act: -0.0001

Data Index: 861013 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1068951 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0625. Min Act: -0.0001

Data Index: 601013 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0642. Min Act: -0.0001

Data Index: 394304 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1358838 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1157159 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0558. Min Act: -0.0001

Data Index: 698813 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1248619 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0551. Min Act: -0.0000

Data Index: 439043 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0545. Min Act: -0.0000

Data Index: 964792 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1046469 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0529. Min Act: -0.0001

Data Index: 957540 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0542. Min Act: -0.0000

Data Index: 227617 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1654948 (Python Code)

Max Activating Token Index: 865

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0602. Min Act: -0.0001

Data Index: 654379 (C4 (Web Text))

Max Activating Token Index: 411