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

Dataset: The Pile

Neuron 4674 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: 5.4258. Min Range: -5.4258

Max Act: 5.4242. Min Act: -0.0000

Data Index: 1489439 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 5.4258. Min Range: -5.4258

Max Act: 5.0666. Min Act: -0.0000

Data Index: 944772 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 5.4258. Min Range: -5.4258

Max Act: 5.1537. Min Act: -0.0000

Data Index: 1372651 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.9800. Min Act: -0.0000

Data Index: 1633178 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 5.4258. Min Range: -5.4258

Max Act: 5.4258. Min Act: -0.0000

Data Index: 388475 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.8093. Min Act: -0.0000

Data Index: 1597193 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 5.4258. Min Range: -5.4258

Max Act: 5.2820. Min Act: -0.0000

Data Index: 1199810 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.9492. Min Act: -0.0000

Data Index: 1774664 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.8912. Min Act: -0.0000

Data Index: 1590420 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 5.4258. Min Range: -5.4258

Max Act: 5.0480. Min Act: -0.0000

Data Index: 1538087 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.6856. Min Act: -0.0000

Data Index: 1101597 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.9675. Min Act: -0.0000

Data Index: 1166546 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.8095. Min Act: -0.0000

Data Index: 625997 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.7834. Min Act: -0.0000

Data Index: 1428556 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.9414. Min Act: -0.0000

Data Index: 363782 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.7097. Min Act: -0.0000

Data Index: 31702 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.8899. Min Act: -0.0000

Data Index: 902965 (The Pile)

Max Activating Token Index: 181

Text #17

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.4868. Min Act: -0.0000

Data Index: 1673032 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.5065. Min Act: -0.0000

Data Index: 1794414 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 5.4258. Min Range: -5.4258

Max Act: 4.5336. Min Act: -0.0000

Data Index: 616585 (The Pile)

Max Activating Token Index: 764