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

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

Neuron 2098 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: 1.0848. Min Range: -1.0848

Max Act: 1.0848. Min Act: -0.0000

Data Index: 1029339 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9286. Min Act: -0.0000

Data Index: 276815 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9101. Min Act: -0.0001

Data Index: 1341562 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1239743 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9782. Min Act: -0.0001

Data Index: 1333674 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8445. Min Act: -0.0001

Data Index: 590745 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8243. Min Act: -0.0001

Data Index: 760173 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8892. Min Act: -0.0000

Data Index: 526651 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8388. Min Act: -0.0000

Data Index: 127716 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7222. Min Act: -0.0000

Data Index: 787830 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8106. Min Act: -0.0001

Data Index: 1339570 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8856. Min Act: -0.0000

Data Index: 246624 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9436. Min Act: -0.0000

Data Index: 48633 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7685. Min Act: -0.0001

Data Index: 1272497 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7920. Min Act: -0.0000

Data Index: 280911 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1183361 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8068. Min Act: -0.0000

Data Index: 918542 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7197. Min Act: -0.0001

Data Index: 54081 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8033. Min Act: -0.0000

Data Index: 397128 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8108. Min Act: -0.0000

Data Index: 350509 (C4 (Web Text))

Max Activating Token Index: 656