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

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

Neuron 224 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9286. Min Act: -0.0000

Data Index: 880933 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9517. Min Act: -0.0000

Data Index: 368408 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1007937 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1323779 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.0005. Min Range: -1.0005

Max Act: 1.0005. Min Act: -0.0000

Data Index: 472345 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8427. Min Act: -0.0000

Data Index: 760013 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8366. Min Act: -0.0000

Data Index: 710034 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1260048 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8129. Min Act: -0.0000

Data Index: 983303 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1157891 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8220. Min Act: -0.0000

Data Index: 15956 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8331. Min Act: -0.0000

Data Index: 607243 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7377. Min Act: -0.0000

Data Index: 95543 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1125283 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7857. Min Act: -0.0000

Data Index: 621174 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7210. Min Act: -0.0000

Data Index: 458520 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.6927. Min Act: -0.0000

Data Index: 923849 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.6850. Min Act: -0.0000

Data Index: 820889 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.6956. Min Act: -0.0000

Data Index: 339329 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.6709. Min Act: -0.0000

Data Index: 135036 (C4 (Web Text))

Max Activating Token Index: 394