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

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

Neuron 2348 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3877. Min Act: -0.0001

Data Index: 905076 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1285853 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3212. Min Act: -0.0001

Data Index: 503643 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3335. Min Act: -0.0001

Data Index: 655897 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1122687 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1310993 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.3152. Min Act: -0.0001

Data Index: 355015 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.2393. Min Act: -0.0001

Data Index: 375373 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1932. Min Act: -0.0001

Data Index: 158375 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1943. Min Act: -0.0001

Data Index: 233444 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.2103. Min Act: -0.0001

Data Index: 13697 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1775. Min Act: -0.0001

Data Index: 1216747 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1797. Min Act: -0.0001

Data Index: 416219 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1828. Min Act: -0.0001

Data Index: 112848 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1836. Min Act: -0.0001

Data Index: 616494 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1839. Min Act: -0.0001

Data Index: 489172 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1245204 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1284111 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1719. Min Act: -0.0001

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.3877. Min Range: -0.3877

Max Act: 0.1526. Min Act: -0.0001

Data Index: 859113 (C4 (Web Text))

Max Activating Token Index: 372