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

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

Neuron 270 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0001

Data Index: 720851 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0897. Min Act: -0.0001

Data Index: 265671 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0740. Min Act: -0.0001

Data Index: 929677 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0729. Min Act: -0.0001

Data Index: 594629 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0740. Min Act: -0.0001

Data Index: 970723 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0681. Min Act: -0.0001

Data Index: 682050 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0723. Min Act: -0.0001

Data Index: 555482 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1305082 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0678. Min Act: -0.0001

Data Index: 817855 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0673. Min Act: -0.0001

Data Index: 94927 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0644. Min Act: -0.0001

Data Index: 984661 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1236800 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0636. Min Act: -0.0001

Data Index: 628920 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0682. Min Act: -0.0001

Data Index: 89049 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0660. Min Act: -0.0001

Data Index: 846906 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1384 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0633. Min Act: -0.0001

Data Index: 447898 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0622. Min Act: -0.0001

Data Index: 469846 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0643. Min Act: -0.0001

Data Index: 851552 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0619. Min Act: -0.0001

Data Index: 829602 (C4 (Web Text))

Max Activating Token Index: 250