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

Dataset: The Pile

Neuron 847 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.9641. Min Act: -0.0000

Data Index: 1839360 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.7863. Min Act: -0.0000

Data Index: 1105098 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.8840. Min Act: -0.0000

Data Index: 586389 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.6427. Min Act: -0.0000

Data Index: 1675415 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.6051. Min Act: -0.0001

Data Index: 1643484 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.4866. Min Act: -0.0000

Data Index: 1673038 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.3126. Min Act: -0.0000

Data Index: 423661 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.1471. Min Act: -0.0000

Data Index: 132678 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.2946. Min Act: -0.0000

Data Index: 1892958 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.5726. Min Act: -0.0000

Data Index: 1385777 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.2700. Min Act: -0.0000

Data Index: 485722 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.4000. Min Act: -0.0000

Data Index: 1087727 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.3629. Min Act: -0.0000

Data Index: 389203 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.4880. Min Act: -0.0000

Data Index: 71730 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.4729. Min Act: -0.0000

Data Index: 1212890 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.1888. Min Act: -0.0000

Data Index: 1055727 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.2797. Min Act: -0.0000

Data Index: 1464662 (The Pile)

Max Activating Token Index: 305

Text #17

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.2762. Min Act: -0.0000

Data Index: 79974 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.2631. Min Act: -0.0000

Data Index: 1664874 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 3.9641. Min Range: -3.9641

Max Act: 3.3211. Min Act: -0.0000

Data Index: 1987211 (The Pile)

Max Activating Token Index: 313