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

Dataset: The Pile

Neuron 547 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: 0.7030. Min Range: -0.7030

Max Act: 0.7030. Min Act: 0.0000

Data Index: 622509 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1897564 (The Pile)

Max Activating Token Index: 535

Text #2

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5884. Min Act: -0.0000

Data Index: 728970 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.5603. Min Act: 0.0000

Data Index: 1570327 (The Pile)

Max Activating Token Index: 664

Text #4

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4900. Min Act: -0.0000

Data Index: 951922 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4876. Min Act: 0.0000

Data Index: 1922976 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4668. Min Act: 0.0000

Data Index: 1125708 (The Pile)

Max Activating Token Index: 102

Text #7

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1067826 (The Pile)

Max Activating Token Index: 841

Text #8

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4714. Min Act: -0.0000

Data Index: 394146 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4725. Min Act: -0.0000

Data Index: 940517 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1230102 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1349988 (The Pile)

Max Activating Token Index: 327

Text #12

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4277. Min Act: 0.0000

Data Index: 1470781 (The Pile)

Max Activating Token Index: 441

Text #13

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.3982. Min Act: -0.0000

Data Index: 441184 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4141. Min Act: -0.0000

Data Index: 558808 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4095. Min Act: -0.0000

Data Index: 76792 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.3792. Min Act: -0.0000

Data Index: 128816 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1640018 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.3876. Min Act: -0.0000

Data Index: 23212 (The Pile)

Max Activating Token Index: 80

Text #19

Max Range: 0.7030. Min Range: -0.7030

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1510283 (The Pile)

Max Activating Token Index: 42