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

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

Neuron 905 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: 2.0710. Min Range: -2.0710

Max Act: 2.0710. Min Act: -0.0000

Data Index: 774338 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1325853 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.4694. Min Act: -0.0000

Data Index: 672130 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.3541. Min Act: -0.0000

Data Index: 908389 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.2592. Min Act: -0.0000

Data Index: 735743 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.1308. Min Act: -0.0000

Data Index: 447964 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.1714. Min Act: -0.0000

Data Index: 808588 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.1590. Min Act: -0.0000

Data Index: 575426 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.1610. Min Act: -0.0000

Data Index: 1322542 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.1235. Min Act: -0.0000

Data Index: 445391 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1340048 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.1250. Min Act: -0.0000

Data Index: 849056 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1030828 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1276865 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 2.0710. Min Range: -2.0710

Max Act: 0.9434. Min Act: -0.0000

Data Index: 208917 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.0983. Min Act: -0.0000

Data Index: 576522 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1137885 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.0015. Min Act: -0.0000

Data Index: 846119 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 2.0710. Min Range: -2.0710

Max Act: 0.8879. Min Act: -0.0000

Data Index: 257266 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 2.0710. Min Range: -2.0710

Max Act: 1.0629. Min Act: -0.0000

Data Index: 164418 (C4 (Web Text))

Max Activating Token Index: 739