Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3600 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.3344. Min Act: -0.0001

Data Index: 1225987 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.3257. Min Act: -0.0002

Data Index: 62438 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.3127. Min Act: -0.0001

Data Index: 895595 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.3155. Min Act: -0.0001

Data Index: 788281 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2973. Min Act: -0.0002

Data Index: 649003 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2917. Min Act: -0.0002

Data Index: 720024 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2830. Min Act: -0.0002

Data Index: 685458 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2804. Min Act: -0.0001

Data Index: 452480 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.3013. Min Act: -0.0002

Data Index: 1001481 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2728. Min Act: -0.0001

Data Index: 618827 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2934. Min Act: -0.0002

Data Index: 855746 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2769. Min Act: -0.0001

Data Index: 646131 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2722. Min Act: -0.0002

Data Index: 161670 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2659. Min Act: -0.0002

Data Index: 666467 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2557. Min Act: -0.0002

Data Index: 17977 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2732. Min Act: -0.0002

Data Index: 468520 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2691. Min Act: -0.0002

Data Index: 478303 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2504. Min Act: -0.0002

Data Index: 134401 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2767. Min Act: -0.0001

Data Index: 670998 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2818. Min Act: -0.0002

Data Index: 110635 (C4 (Web Text))

Max Activating Token Index: 903