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

Dataset: The Pile

Neuron 1674 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: 1.3896. Min Range: -1.3896

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1502248 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1478078 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3146. Min Act: -0.0000

Data Index: 1192581 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3160. Min Act: -0.0000

Data Index: 1737223 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2723. Min Act: -0.0000

Data Index: 835174 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1610085 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1921. Min Act: -0.0000

Data Index: 823220 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2423. Min Act: -0.0000

Data Index: 299175 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1688. Min Act: -0.0000

Data Index: 992662 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2683. Min Act: -0.0000

Data Index: 17389 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1312515 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1030363 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1762. Min Act: -0.0000

Data Index: 363872 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2055. Min Act: -0.0000

Data Index: 34785 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1264324 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1621. Min Act: -0.0000

Data Index: 749769 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2015. Min Act: -0.0000

Data Index: 1725179 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1679017 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1051. Min Act: -0.0000

Data Index: 471761 (The Pile)

Max Activating Token Index: 1010

Text #19

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2223. Min Act: -0.0000

Data Index: 1078759 (The Pile)

Max Activating Token Index: 412