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

Dataset: The Pile

Neuron 2463 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: 0.6639. Min Range: -0.6639

Max Act: 0.6639. Min Act: -0.0000

Data Index: 638647 (The Pile)

Max Activating Token Index: 736

Text #1

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5891. Min Act: -0.0000

Data Index: 199903 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5620. Min Act: -0.0000

Data Index: 923793 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1540576 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5087. Min Act: -0.0000

Data Index: 389490 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1013250 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4852. Min Act: -0.0000

Data Index: 965975 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4694. Min Act: -0.0000

Data Index: 328444 (The Pile)

Max Activating Token Index: 996

Text #8

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1544535 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1831878 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4209. Min Act: -0.0000

Data Index: 284624 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1234826 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4090. Min Act: -0.0000

Data Index: 658958 (The Pile)

Max Activating Token Index: 74

Text #13

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1771810 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1110932 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4041. Min Act: -0.0000

Data Index: 417757 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.3822. Min Act: -0.0000

Data Index: 523828 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1003023 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.3932. Min Act: -0.0000

Data Index: 898153 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.3937. Min Act: -0.0000

Data Index: 46367 (The Pile)

Max Activating Token Index: 264