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

Dataset: The Pile

Neuron 4659 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: 1.0051. Min Range: -1.0051

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1706991 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1528379 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1553112 (The Pile)

Max Activating Token Index: 490

Text #3

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7578. Min Act: -0.0000

Data Index: 742681 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8263. Min Act: -0.0000

Data Index: 666291 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1447849 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1814685 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8834. Min Act: -0.0000

Data Index: 571129 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1041187 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7218. Min Act: -0.0000

Data Index: 947519 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.8419. Min Act: -0.0000

Data Index: 703980 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1845071 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7288. Min Act: -0.0000

Data Index: 481461 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1706456 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1139972 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7552. Min Act: -0.0000

Data Index: 884750 (The Pile)

Max Activating Token Index: 840

Text #16

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1547939 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.6892. Min Act: -0.0000

Data Index: 739059 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.7037. Min Act: -0.0000

Data Index: 758867 (The Pile)

Max Activating Token Index: 714

Text #19

Max Range: 1.0051. Min Range: -1.0051

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1267867 (The Pile)

Max Activating Token Index: 953