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

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

Neuron 1506 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.1700. Min Act: -0.0000

Data Index: 612675 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.1902. Min Act: -0.0000

Data Index: 688106 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0840. Min Act: -0.0000

Data Index: 151283 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0286. Min Act: -0.0000

Data Index: 974442 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1306327 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1325556 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0013. Min Act: -0.0000

Data Index: 413415 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0213. Min Act: -0.0000

Data Index: 526957 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9868. Min Act: -0.0000

Data Index: 211445 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1024870 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9106. Min Act: -0.0000

Data Index: 476070 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1342035 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8931. Min Act: -0.0000

Data Index: 915631 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1283232 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8897. Min Act: -0.0000

Data Index: 975862 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8073. Min Act: -0.0000

Data Index: 524735 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8279. Min Act: -0.0000

Data Index: 550819 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.7476. Min Act: -0.0000

Data Index: 781007 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.7387. Min Act: -0.0000

Data Index: 990591 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.7732. Min Act: -0.0000

Data Index: 606889 (C4 (Web Text))

Max Activating Token Index: 924