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

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

Neuron 2697 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: 0.0861. Min Range: -0.0861

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1312760 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0814. Min Act: -0.0001

Data Index: 627080 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0001

Data Index: 871494 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 641752 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 237385 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 975754 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 723562 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 739092 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 634581 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1302840 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 701274 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1091892 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0767. Min Act: -0.0001

Data Index: 324479 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0795. Min Act: -0.0001

Data Index: 277216 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0771. Min Act: -0.0001

Data Index: 877437 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0767. Min Act: -0.0000

Data Index: 572652 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0743. Min Act: -0.0000

Data Index: 545709 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0681. Min Act: -0.0000

Data Index: 953403 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1240530 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0726. Min Act: -0.0000

Data Index: 64641 (C4 (Web Text))

Max Activating Token Index: 27