Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1088 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0777. Min Act: -0.0006

Data Index: 991873 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0782. Min Act: -0.0006

Data Index: 1259781 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0766. Min Act: -0.0005

Data Index: 881368 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0703. Min Act: -0.0005

Data Index: 457441 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0720. Min Act: -0.0006

Data Index: 945870 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0744. Min Act: -0.0006

Data Index: 152655 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0713. Min Act: -0.0005

Data Index: 1110962 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0720. Min Act: -0.0006

Data Index: 695581 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0711. Min Act: -0.0005

Data Index: 572507 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0711. Min Act: -0.0005

Data Index: 421541 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0687. Min Act: -0.0006

Data Index: 4754 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0652. Min Act: -0.0005

Data Index: 1129143 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0636. Min Act: -0.0006

Data Index: 798090 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0686. Min Act: -0.0006

Data Index: 774260 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0673. Min Act: -0.0005

Data Index: 921806 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0710. Min Act: -0.0006

Data Index: 840572 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0654. Min Act: -0.0006

Data Index: 1204758 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0664. Min Act: -0.0005

Data Index: 699911 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0606. Min Act: -0.0006

Data Index: 316418 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0629. Min Act: -0.0006

Data Index: 1075264 (C4 (Web Text))

Max Activating Token Index: 407