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

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

Neuron 2698 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: 0.6086. Min Range: -0.6086

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1508449 (Python Code)

Max Activating Token Index: 523

Text #1

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.5843. Min Act: 0.0000

Data Index: 549691 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4879. Min Act: 0.0001

Data Index: 626336 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1213758 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4825. Min Act: -0.0000

Data Index: 678037 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4952. Min Act: -0.0000

Data Index: 511152 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4667. Min Act: 0.0002

Data Index: 276494 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4744. Min Act: -0.0000

Data Index: 545279 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4747. Min Act: -0.0000

Data Index: 906340 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4437. Min Act: -0.0000

Data Index: 610484 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4569. Min Act: 0.0000

Data Index: 1495714 (Python Code)

Max Activating Token Index: 384

Text #11

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1517343 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1560655 (Python Code)

Max Activating Token Index: 103

Text #13

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4418. Min Act: -0.0000

Data Index: 228629 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4362. Min Act: -0.0000

Data Index: 368948 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1277591 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4050. Min Act: 0.0000

Data Index: 1634467 (Python Code)

Max Activating Token Index: 386

Text #17

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3915. Min Act: 0.0000

Data Index: 765290 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4101. Min Act: 0.0000

Data Index: 1037198 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4071. Min Act: -0.0000

Data Index: 153341 (C4 (Web Text))

Max Activating Token Index: 58