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

Dataset: The Pile

Neuron 3109 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: 4.0769. Min Range: -4.0769

Max Act: 4.0769. Min Act: -0.0000

Data Index: 498433 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.8407. Min Act: -0.0000

Data Index: 1868111 (The Pile)

Max Activating Token Index: 731

Text #2

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.9694. Min Act: -0.0000

Data Index: 385882 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.6069. Min Act: -0.0000

Data Index: 1384508 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.8387. Min Act: -0.0000

Data Index: 1888156 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.4186. Min Act: -0.0000

Data Index: 747464 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.4063. Min Act: -0.0000

Data Index: 1169505 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.4268. Min Act: -0.0000

Data Index: 397166 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.6003. Min Act: -0.0000

Data Index: 647352 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.4174. Min Act: -0.0000

Data Index: 728734 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.2003. Min Act: -0.0000

Data Index: 875840 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 4.0769. Min Range: -4.0769

Max Act: 2.8742. Min Act: -0.0000

Data Index: 123602 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.1680. Min Act: -0.0000

Data Index: 1701418 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.6379. Min Act: -0.0000

Data Index: 724792 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 4.0769. Min Range: -4.0769

Max Act: 2.9841. Min Act: -0.0000

Data Index: 1893439 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 4.0769. Min Range: -4.0769

Max Act: 2.9710. Min Act: -0.0000

Data Index: 1746565 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.2109. Min Act: -0.0000

Data Index: 891678 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.2240. Min Act: -0.0000

Data Index: 972540 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.0734. Min Act: -0.0000

Data Index: 1637049 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 4.0769. Min Range: -4.0769

Max Act: 3.0507. Min Act: -0.0000

Data Index: 1008497 (The Pile)

Max Activating Token Index: 663