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

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

Neuron 2330 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.7248. Min Act: -0.0001

Data Index: 554236 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.7115. Min Act: -0.0001

Data Index: 1057120 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5417. Min Act: -0.0001

Data Index: 1029010 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5802. Min Act: -0.0001

Data Index: 125298 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5563. Min Act: -0.0001

Data Index: 727171 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5350. Min Act: -0.0001

Data Index: 1235848 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.4945. Min Act: -0.0001

Data Index: 575622 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.4868. Min Act: -0.0001

Data Index: 883027 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.4948. Min Act: -0.0001

Data Index: 671881 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.4387. Min Act: -0.0001

Data Index: 1048689 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.4121. Min Act: -0.0001

Data Index: 1018638 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.3766. Min Act: -0.0001

Data Index: 254450 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.3550. Min Act: -0.0001

Data Index: 29820 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.3534. Min Act: -0.0001

Data Index: 157574 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.3604. Min Act: -0.0001

Data Index: 605532 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.3418. Min Act: -0.0001

Data Index: 817520 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.3328. Min Act: -0.0001

Data Index: 675354 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.2964. Min Act: -0.0001

Data Index: 992300 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.3107. Min Act: -0.0001

Data Index: 34510 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.2684. Min Act: -0.0001

Data Index: 6453 (C4 (Web Text))

Max Activating Token Index: 845