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

Dataset: The Pile

Neuron 882 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.7651. Min Act: -0.0000

Data Index: 638061 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.5213. Min Act: -0.0000

Data Index: 1037804 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3498. Min Act: -0.0000

Data Index: 749596 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.5104. Min Act: -0.0000

Data Index: 1026013 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3309. Min Act: -0.0000

Data Index: 250071 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2617. Min Act: -0.0000

Data Index: 19315 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3106. Min Act: -0.0000

Data Index: 562903 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1585274 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1255. Min Act: -0.0000

Data Index: 433957 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2769. Min Act: -0.0000

Data Index: 1199708 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1191697 (The Pile)

Max Activating Token Index: 464

Text #11

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1645158 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1455. Min Act: -0.0000

Data Index: 522511 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1220. Min Act: -0.0000

Data Index: 58712 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1559803 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0324. Min Act: -0.0000

Data Index: 151538 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1903516 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1245914 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 1.7651. Min Range: -1.7651

Max Act: 0.9540. Min Act: -0.0000

Data Index: 827567 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0608. Min Act: -0.0000

Data Index: 848795 (The Pile)

Max Activating Token Index: 842