Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 429 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5840. Min Act: -0.0000

Data Index: 413098 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5489. Min Act: -0.0000

Data Index: 355255 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.6072. Min Act: -0.0000

Data Index: 1871791 (The Pile)

Max Activating Token Index: 524

Text #3

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4590. Min Act: -0.0000

Data Index: 307831 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4992. Min Act: -0.0000

Data Index: 693829 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5926. Min Act: -0.0000

Data Index: 607760 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5566. Min Act: -0.0000

Data Index: 1077614 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1118275 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4672. Min Act: -0.0000

Data Index: 259892 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4205. Min Act: -0.0000

Data Index: 1135498 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.6767. Min Act: -0.0000

Data Index: 1599595 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5228. Min Act: -0.0000

Data Index: 31185 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1085096 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4561. Min Act: -0.0000

Data Index: 995403 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.3856. Min Act: -0.0000

Data Index: 351625 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5262. Min Act: -0.0000

Data Index: 608435 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1250867 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.3810. Min Act: -0.0000

Data Index: 1709102 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1824781 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1691030 (The Pile)

Max Activating Token Index: 617