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

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

Neuron 2672 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6931. Min Act: -0.0000

Data Index: 327762 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5766. Min Act: -0.0000

Data Index: 20773 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5189. Min Act: -0.0000

Data Index: 361512 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5149. Min Act: -0.0000

Data Index: 717796 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5038. Min Act: -0.0000

Data Index: 369729 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5002. Min Act: -0.0000

Data Index: 746013 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4918. Min Act: -0.0000

Data Index: 530866 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4859. Min Act: -0.0000

Data Index: 167147 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4889. Min Act: -0.0000

Data Index: 714870 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4556. Min Act: -0.0000

Data Index: 78070 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1143237 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4692. Min Act: -0.0000

Data Index: 908255 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4597. Min Act: -0.0000

Data Index: 871651 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4606. Min Act: -0.0000

Data Index: 915060 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4048. Min Act: -0.0000

Data Index: 555104 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4403. Min Act: -0.0000

Data Index: 60462 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1031291 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4420. Min Act: -0.0000

Data Index: 955596 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4588. Min Act: -0.0000

Data Index: 171592 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4030. Min Act: -0.0000

Data Index: 376678 (C4 (Web Text))

Max Activating Token Index: 129