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

Dataset: The Pile

Neuron 3655 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: 1.0758. Min Range: -1.0758

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1996581 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9676. Min Act: -0.0000

Data Index: 537315 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9685. Min Act: -0.0000

Data Index: 870972 (The Pile)

Max Activating Token Index: 200

Text #3

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1919319 (The Pile)

Max Activating Token Index: 599

Text #4

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9050. Min Act: -0.0000

Data Index: 207359 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8631. Min Act: -0.0000

Data Index: 774218 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1353253 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1213173 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9060. Min Act: -0.0000

Data Index: 925440 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1815686 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1388610 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1598598 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1671875 (The Pile)

Max Activating Token Index: 755

Text #13

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7936. Min Act: -0.0000

Data Index: 637334 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1874421 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1884443 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8141. Min Act: -0.0000

Data Index: 739509 (The Pile)

Max Activating Token Index: 18

Text #17

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.7382. Min Act: -0.0000

Data Index: 424600 (The Pile)

Max Activating Token Index: 674

Text #18

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8322. Min Act: -0.0000

Data Index: 39671 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.8303. Min Act: -0.0000

Data Index: 827511 (The Pile)

Max Activating Token Index: 851