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

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

Neuron 3532 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5624. Min Act: -0.0001

Data Index: 571783 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4705. Min Act: -0.0001

Data Index: 735851 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4174. Min Act: -0.0001

Data Index: 415264 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3910. Min Act: -0.0001

Data Index: 173948 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3892. Min Act: -0.0001

Data Index: 861591 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3858. Min Act: -0.0001

Data Index: 699907 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3550. Min Act: -0.0001

Data Index: 215483 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3427. Min Act: -0.0001

Data Index: 111508 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3410. Min Act: -0.0001

Data Index: 1166880 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3376. Min Act: -0.0001

Data Index: 1018781 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3340. Min Act: -0.0001

Data Index: 391585 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3321. Min Act: -0.0001

Data Index: 1042001 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3239. Min Act: -0.0001

Data Index: 1303468 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3230. Min Act: -0.0001

Data Index: 91454 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3255. Min Act: -0.0001

Data Index: 179776 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3360. Min Act: -0.0001

Data Index: 1270847 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.2860. Min Act: -0.0001

Data Index: 1072538 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3043. Min Act: -0.0001

Data Index: 376091 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3108. Min Act: -0.0001

Data Index: 803760 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3202. Min Act: -0.0001

Data Index: 989177 (C4 (Web Text))

Max Activating Token Index: 394