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

Dataset: The Pile

Neuron 4641 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: 1.5528. Min Range: -1.5528

Max Act: 1.5528. Min Act: -0.0000

Data Index: 142171 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 1.5528. Min Range: -1.5528

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1381738 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.9648. Min Act: -0.0000

Data Index: 192130 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1191576 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.9641. Min Act: -0.0000

Data Index: 529543 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.8517. Min Act: -0.0000

Data Index: 124137 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.8733. Min Act: -0.0000

Data Index: 612903 (The Pile)

Max Activating Token Index: 158

Text #7

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.9016. Min Act: -0.0000

Data Index: 666522 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.8240. Min Act: -0.0000

Data Index: 375081 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1714954 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1497498 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.8545. Min Act: -0.0000

Data Index: 125067 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.8486. Min Act: -0.0000

Data Index: 966360 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1235939 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.8257. Min Act: -0.0000

Data Index: 377364 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.7861. Min Act: -0.0000

Data Index: 484023 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1054580 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.8077. Min Act: -0.0000

Data Index: 366685 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1110924 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 1.5528. Min Range: -1.5528

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1359521 (The Pile)

Max Activating Token Index: 81