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

Dataset: The Pile

Neuron 4307 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: 0.5621. Min Range: -0.5621

Max Act: 0.4742. Min Act: -0.0000

Data Index: 838816 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1157455 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5155. Min Act: -0.0000

Data Index: 110071 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1740755 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1979865 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4909. Min Act: -0.0000

Data Index: 64491 (The Pile)

Max Activating Token Index: 349

Text #6

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5371. Min Act: -0.0000

Data Index: 724155 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1807264 (The Pile)

Max Activating Token Index: 652

Text #8

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1254480 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4946. Min Act: 0.0000

Data Index: 1501857 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5097. Min Act: 0.0000

Data Index: 66096 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4782. Min Act: -0.0000

Data Index: 242278 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4465. Min Act: -0.0000

Data Index: 335151 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4948. Min Act: 0.0000

Data Index: 302172 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1628698 (The Pile)

Max Activating Token Index: 389

Text #15

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4814. Min Act: -0.0000

Data Index: 331067 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5040. Min Act: -0.0000

Data Index: 706461 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4723. Min Act: -0.0000

Data Index: 932760 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4472. Min Act: 0.0000

Data Index: 513149 (The Pile)

Max Activating Token Index: 416

Text #19

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4718. Min Act: 0.0000

Data Index: 1229763 (The Pile)

Max Activating Token Index: 895