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

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

Neuron 1263 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3207. Min Range: -1.3207

Max Act: 1.3207. Min Act: -0.0000

Data Index: 379548 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1223840 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 1.3207. Min Range: -1.3207

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1337977 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.9558. Min Act: -0.0000

Data Index: 477126 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1292611 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1247633 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8730. Min Act: -0.0000

Data Index: 501714 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.9666. Min Act: -0.0000

Data Index: 448849 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.9091. Min Act: -0.0000

Data Index: 613343 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8696. Min Act: -0.0000

Data Index: 564550 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8884. Min Act: -0.0000

Data Index: 168404 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8729. Min Act: -0.0000

Data Index: 508761 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8350. Min Act: -0.0000

Data Index: 2541 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8521. Min Act: -0.0000

Data Index: 621978 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8524. Min Act: -0.0000

Data Index: 955668 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8572. Min Act: -0.0000

Data Index: 683191 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.7807. Min Act: -0.0000

Data Index: 356242 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.7642. Min Act: -0.0000

Data Index: 393855 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.8362. Min Act: -0.0000

Data Index: 135640 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.3207. Min Range: -1.3207

Max Act: 0.7811. Min Act: -0.0000

Data Index: 23453 (C4 (Web Text))

Max Activating Token Index: 890