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

Dataset: The Pile

Neuron 3644 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0000

Data Index: 209555 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1166079 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1321742 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1233256 (The Pile)

Max Activating Token Index: 994

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1158834 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0770. Min Act: -0.0000

Data Index: 318417 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1124966 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1943152 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0689. Min Act: -0.0000

Data Index: 761750 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1000421 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0691. Min Act: -0.0000

Data Index: 581094 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1860164 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1792824 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0667. Min Act: -0.0000

Data Index: 126429 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0671. Min Act: -0.0000

Data Index: 88974 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1908161 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1881789 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0662. Min Act: 0.0000

Data Index: 1927799 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1331225 (The Pile)

Max Activating Token Index: 975

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1267950 (The Pile)

Max Activating Token Index: 97