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

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

Neuron 3432 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1517. Min Act: -0.0000

Data Index: 683758 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1282. Min Act: -0.0000

Data Index: 986387 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1000. Min Act: -0.0001

Data Index: 158169 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0929. Min Act: -0.0000

Data Index: 557486 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0902. Min Act: -0.0000

Data Index: 767680 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1154459 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0859. Min Act: -0.0000

Data Index: 298921 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0841. Min Act: -0.0000

Data Index: 568942 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1326496 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0819. Min Act: -0.0000

Data Index: 809405 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1068871 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1090632 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0816. Min Act: -0.0000

Data Index: 970137 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1339253 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0747. Min Act: -0.0000

Data Index: 353935 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0792. Min Act: -0.0000

Data Index: 798707 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0781. Min Act: -0.0001

Data Index: 998549 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0752. Min Act: -0.0000

Data Index: 110137 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1270929 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0766. Min Act: -0.0000

Data Index: 393979 (C4 (Web Text))

Max Activating Token Index: 305