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

Dataset: The Pile

Neuron 3553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1039617 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.7234. Min Act: -0.0000

Data Index: 557696 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.7297. Min Act: -0.0000

Data Index: 508240 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1467999 (The Pile)

Max Activating Token Index: 115

Text #4

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1928107 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6505. Min Act: -0.0000

Data Index: 610213 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5992. Min Act: -0.0000

Data Index: 395546 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5765. Min Act: -0.0000

Data Index: 96886 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1199408 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6151. Min Act: -0.0000

Data Index: 964033 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5978. Min Act: -0.0000

Data Index: 414451 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5661. Min Act: -0.0000

Data Index: 426593 (The Pile)

Max Activating Token Index: 881

Text #12

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1071441 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1318875 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5879. Min Act: -0.0000

Data Index: 929838 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1014994 (The Pile)

Max Activating Token Index: 669

Text #16

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5682. Min Act: -0.0000

Data Index: 597910 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1870591 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5863. Min Act: -0.0000

Data Index: 224303 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1728803 (The Pile)

Max Activating Token Index: 296