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

Dataset: The Pile

Neuron 3845 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.8099. Min Act: -0.0000

Data Index: 27838 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6825. Min Act: -0.0000

Data Index: 897265 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6930. Min Act: -0.0000

Data Index: 681325 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6681. Min Act: -0.0000

Data Index: 787631 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1372664 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6570. Min Act: -0.0000

Data Index: 623780 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1436446 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1967978 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1129357 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1234828 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1588883 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1986780 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5942. Min Act: -0.0000

Data Index: 94043 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5686. Min Act: -0.0000

Data Index: 369978 (The Pile)

Max Activating Token Index: 413

Text #14

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5586. Min Act: -0.0000

Data Index: 398310 (The Pile)

Max Activating Token Index: 788

Text #15

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.6305. Min Act: -0.0000

Data Index: 160136 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5178. Min Act: -0.0000

Data Index: 193086 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5682. Min Act: -0.0000

Data Index: 193588 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1634638 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 0.8099. Min Range: -0.8099

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1222459 (The Pile)

Max Activating Token Index: 61