Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 39 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.2006. Min Act: -0.0000

Data Index: 180982 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1264837 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1258184 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8999. Min Act: -0.0000

Data Index: 902818 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.7913. Min Act: -0.0000

Data Index: 689977 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.7728. Min Act: -0.0000

Data Index: 235121 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1050993 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1290446 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.7330. Min Act: -0.0000

Data Index: 211014 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1030821 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.7171. Min Act: -0.0000

Data Index: 312354 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1132037 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.6810. Min Act: -0.0000

Data Index: 452438 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.6569. Min Act: -0.0000

Data Index: 983162 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.6728. Min Act: -0.0000

Data Index: 734047 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.6506. Min Act: -0.0000

Data Index: 280666 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.6466. Min Act: -0.0000

Data Index: 378227 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1005508 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.6464. Min Act: -0.0000

Data Index: 406787 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1006692 (C4 (Web Text))

Max Activating Token Index: 44