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

Dataset: The Pile

Neuron 3178 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5041. Min Range: -4.5041

Max Act: 4.5041. Min Act: -0.0000

Data Index: 775013 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.8250. Min Act: -0.0000

Data Index: 1502619 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.8595. Min Act: -0.0000

Data Index: 1639086 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.6020. Min Act: -0.0000

Data Index: 1156343 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.5105. Min Act: -0.0000

Data Index: 666595 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.6470. Min Act: -0.0000

Data Index: 398446 (The Pile)

Max Activating Token Index: 422

Text #6

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.6376. Min Act: -0.0000

Data Index: 107 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.4598. Min Act: -0.0000

Data Index: 782816 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.4257. Min Act: -0.0000

Data Index: 412710 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.5532. Min Act: -0.0000

Data Index: 1370807 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.3766. Min Act: -0.0000

Data Index: 1907924 (The Pile)

Max Activating Token Index: 648

Text #11

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.3683. Min Act: -0.0000

Data Index: 1076328 (The Pile)

Max Activating Token Index: 870

Text #12

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.3149. Min Act: -0.0000

Data Index: 560424 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.2057. Min Act: -0.0000

Data Index: 889851 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.4698. Min Act: -0.0000

Data Index: 756287 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.1603. Min Act: -0.0000

Data Index: 1323561 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.2646. Min Act: -0.0000

Data Index: 1167850 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.2734. Min Act: -0.0000

Data Index: 9874 (The Pile)

Max Activating Token Index: 735

Text #18

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.2326. Min Act: -0.0000

Data Index: 1488722 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 4.5041. Min Range: -4.5041

Max Act: 3.2123. Min Act: -0.0000

Data Index: 646541 (The Pile)

Max Activating Token Index: 900