Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1248 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.7872. Min Act: -0.0001

Data Index: 29146 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6785. Min Act: -0.0001

Data Index: 437724 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6979. Min Act: -0.0001

Data Index: 743347 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6525. Min Act: -0.0001

Data Index: 517062 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6463. Min Act: -0.0001

Data Index: 641962 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6251. Min Act: -0.0001

Data Index: 1143821 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6165. Min Act: -0.0001

Data Index: 349285 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6253. Min Act: -0.0001

Data Index: 871067 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6025. Min Act: -0.0001

Data Index: 951798 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5863. Min Act: -0.0001

Data Index: 377538 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6071. Min Act: -0.0001

Data Index: 109041 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.6032. Min Act: -0.0001

Data Index: 949426 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5748. Min Act: -0.0001

Data Index: 1245239 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5513. Min Act: -0.0001

Data Index: 14265 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5503. Min Act: -0.0001

Data Index: 362447 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5450. Min Act: -0.0001

Data Index: 408924 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5551. Min Act: -0.0001

Data Index: 1154279 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5924. Min Act: -0.0001

Data Index: 66795 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5362. Min Act: -0.0001

Data Index: 1193923 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.7872. Min Range: -0.7872

Max Act: 0.5403. Min Act: -0.0001

Data Index: 858303 (C4 (Web Text))

Max Activating Token Index: 995