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

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

Neuron 530 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.3367. Min Act: -0.0000

Data Index: 441392 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2599. Min Act: -0.0000

Data Index: 180744 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2879. Min Act: -0.0000

Data Index: 404987 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.3128. Min Act: -0.0000

Data Index: 971110 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2281. Min Act: -0.0000

Data Index: 952000 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1300866 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2525. Min Act: -0.0000

Data Index: 599702 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1357658 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.1691. Min Act: -0.0000

Data Index: 163408 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2017. Min Act: -0.0000

Data Index: 507459 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2124. Min Act: -0.0000

Data Index: 1297087 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.1599. Min Act: -0.0000

Data Index: 849640 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.1872. Min Act: -0.0000

Data Index: 393307 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.2196. Min Act: -0.0000

Data Index: 789671 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.1638. Min Act: -0.0000

Data Index: 814723 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.0730. Min Act: -0.0000

Data Index: 489472 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.0887. Min Act: -0.0000

Data Index: 584791 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1078505 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.1563. Min Act: -0.0000

Data Index: 348966 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.1739. Min Act: -0.0000

Data Index: 977486 (C4 (Web Text))

Max Activating Token Index: 883