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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 31 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6780. Min Act: -0.0000

Data Index: 677575 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6128. Min Act: -0.0000

Data Index: 981841 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1083406 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5941. Min Act: -0.0000

Data Index: 89606 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5628. Min Act: -0.0001

Data Index: 447530 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6012. Min Act: -0.0000

Data Index: 989791 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1293494 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5976. Min Act: -0.0000

Data Index: 934129 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1038588 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5589. Min Act: -0.0001

Data Index: 1088502 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4913. Min Act: -0.0000

Data Index: 889526 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5373. Min Act: -0.0000

Data Index: 235671 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1078021 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4828. Min Act: -0.0000

Data Index: 475659 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1334630 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4669. Min Act: -0.0001

Data Index: 342490 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1316839 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4809. Min Act: -0.0001

Data Index: 210889 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4758. Min Act: -0.0000

Data Index: 693381 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1511121 (Python Code)

Max Activating Token Index: 434