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

Dataset: The Pile

Neuron 4729 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.5401. Min Act: -0.0000

Data Index: 280525 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1319840 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.5210. Min Act: -0.0000

Data Index: 421238 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3810. Min Act: -0.0000

Data Index: 1260762 (The Pile)

Max Activating Token Index: 591

Text #4

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.5360. Min Act: -0.0000

Data Index: 472952 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.5123. Min Act: -0.0000

Data Index: 416209 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1668414 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1865188 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2070. Min Act: -0.0000

Data Index: 480907 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2346. Min Act: -0.0000

Data Index: 1904410 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1139236 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2819. Min Act: -0.0000

Data Index: 1125757 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1123782 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1753005 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3188. Min Act: -0.0000

Data Index: 1254628 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1394. Min Act: -0.0000

Data Index: 940192 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1600653 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1140678 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1208. Min Act: -0.0000

Data Index: 901904 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1089. Min Act: -0.0000

Data Index: 177806 (The Pile)

Max Activating Token Index: 330