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

Dataset: The Pile

Neuron 3670 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.8850. Min Act: -0.0000

Data Index: 684778 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.7975. Min Act: -0.0000

Data Index: 870279 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.6944. Min Act: -0.0000

Data Index: 398014 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.6529. Min Act: -0.0000

Data Index: 83929 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.6781. Min Act: -0.0000

Data Index: 589332 (The Pile)

Max Activating Token Index: 475

Text #5

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1963741 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1808898 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.6192. Min Act: -0.0000

Data Index: 902624 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1357134 (The Pile)

Max Activating Token Index: 737

Text #9

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1634158 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1171871 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1300428 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1456208 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5596. Min Act: -0.0000

Data Index: 28367 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5714. Min Act: -0.0000

Data Index: 9694 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5746. Min Act: -0.0000

Data Index: 433300 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1350658 (The Pile)

Max Activating Token Index: 749

Text #17

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5258. Min Act: -0.0000

Data Index: 391902 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.4970. Min Act: -0.0000

Data Index: 148728 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 0.8850. Min Range: -0.8850

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1746705 (The Pile)

Max Activating Token Index: 892