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

Dataset: The Pile

Neuron 1103 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: 1.2506. Min Range: -1.2506

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1840619 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.9990. Min Act: -0.0000

Data Index: 524797 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 1.2506. Min Range: -1.2506

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1034102 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 1.2506. Min Range: -1.2506

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1669608 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 1.2506. Min Range: -1.2506

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1342766 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 1.2506. Min Range: -1.2506

Max Act: 1.0471. Min Act: -0.0000

Data Index: 226727 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1122830 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 1.2506. Min Range: -1.2506

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1819584 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.9640. Min Act: -0.0000

Data Index: 563295 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.9274. Min Act: -0.0000

Data Index: 39503 (The Pile)

Max Activating Token Index: 634

Text #10

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1764486 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.9098. Min Act: -0.0000

Data Index: 409634 (The Pile)

Max Activating Token Index: 831

Text #12

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.9755. Min Act: -0.0000

Data Index: 752297 (The Pile)

Max Activating Token Index: 944

Text #13

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.9246. Min Act: -0.0000

Data Index: 582785 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.8426. Min Act: -0.0000

Data Index: 655231 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.9224. Min Act: -0.0000

Data Index: 399738 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1512377 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.8964. Min Act: -0.0000

Data Index: 198674 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.8664. Min Act: -0.0000

Data Index: 326691 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 1.2506. Min Range: -1.2506

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1226374 (The Pile)

Max Activating Token Index: 945