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

Dataset: The Pile

Neuron 903 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: 0.9675. Min Range: -0.9675

Max Act: 0.9638. Min Act: -0.0000

Data Index: 713395 (The Pile)

Max Activating Token Index: 27

Text #1

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9675. Min Act: -0.0000

Data Index: 915383 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1761694 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9499. Min Act: -0.0000

Data Index: 561858 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1664371 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1101649 (The Pile)

Max Activating Token Index: 190

Text #6

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1426887 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9160. Min Act: -0.0000

Data Index: 138579 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9076. Min Act: -0.0000

Data Index: 423935 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1451307 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9326. Min Act: -0.0000

Data Index: 218584 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8441. Min Act: -0.0000

Data Index: 488615 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1564932 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8878. Min Act: -0.0000

Data Index: 785430 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1047951 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1234329 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1328560 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1992497 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1907565 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 0.9675. Min Range: -0.9675

Max Act: 0.9016. Min Act: -0.0000

Data Index: 756340 (The Pile)

Max Activating Token Index: 101