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

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

Neuron 1916 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: 1.9513. Min Range: -1.9513

Max Act: 1.8117. Min Act: -0.0001

Data Index: 1206574 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.8309. Min Act: -0.0001

Data Index: 111240 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.8845. Min Act: -0.0001

Data Index: 582701 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.8669. Min Act: -0.0001

Data Index: 925113 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.8552. Min Act: -0.0001

Data Index: 692481 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.9513. Min Act: -0.0001

Data Index: 147829 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.8482. Min Act: -0.0001

Data Index: 1033203 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.8315. Min Act: -0.0001

Data Index: 656088 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.8078. Min Act: -0.0001

Data Index: 927922 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.5715. Min Act: -0.0001

Data Index: 925632 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.7585. Min Act: -0.0001

Data Index: 132736 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.6538. Min Act: -0.0001

Data Index: 1048625 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.6430. Min Act: -0.0001

Data Index: 929452 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.7120. Min Act: -0.0001

Data Index: 1313513 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.6278. Min Act: -0.0001

Data Index: 61747 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.7130. Min Act: -0.0001

Data Index: 164362 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.6535. Min Act: -0.0001

Data Index: 496996 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.6800. Min Act: -0.0001

Data Index: 1016097 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.7335. Min Act: -0.0001

Data Index: 609364 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.9513. Min Range: -1.9513

Max Act: 1.4667. Min Act: -0.0001

Data Index: 390426 (C4 (Web Text))

Max Activating Token Index: 117