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

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

Neuron 58 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: 1.1818. Min Range: -1.1818

Max Act: 1.1359. Min Act: -0.0001

Data Index: 777780 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.1818. Min Range: -1.1818

Max Act: 1.1698. Min Act: -0.0001

Data Index: 645072 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.1818. Min Range: -1.1818

Max Act: 1.1792. Min Act: -0.0001

Data Index: 75749 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 1.1818. Min Range: -1.1818

Max Act: 1.1818. Min Act: -0.0001

Data Index: 625065 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 1.1818. Min Range: -1.1818

Max Act: 1.0607. Min Act: -0.0001

Data Index: 92380 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.9431. Min Act: -0.0001

Data Index: 487937 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8335. Min Act: -0.0001

Data Index: 140793 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.9060. Min Act: -0.0001

Data Index: 620396 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.9642. Min Act: -0.0001

Data Index: 1315387 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8667. Min Act: -0.0001

Data Index: 614637 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8700. Min Act: -0.0001

Data Index: 1146813 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8915. Min Act: -0.0001

Data Index: 610589 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1257388 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8763. Min Act: -0.0001

Data Index: 764964 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8357. Min Act: -0.0001

Data Index: 857704 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8175. Min Act: -0.0001

Data Index: 815393 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8721. Min Act: -0.0001

Data Index: 61955 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.9067. Min Act: -0.0001

Data Index: 195210 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.8705. Min Act: -0.0001

Data Index: 737541 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 1.1818. Min Range: -1.1818

Max Act: 0.7872. Min Act: -0.0001

Data Index: 1299202 (C4 (Web Text))

Max Activating Token Index: 323