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

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

Neuron 421 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1584. Min Range: -1.1584

Max Act: 1.1584. Min Act: -0.0000

Data Index: 400041 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9817. Min Act: -0.0000

Data Index: 808548 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1099943 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9243. Min Act: 0.0000

Data Index: 613267 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9718. Min Act: -0.0000

Data Index: 383872 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9711. Min Act: -0.0000

Data Index: 674724 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9522. Min Act: -0.0000

Data Index: 808370 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9361. Min Act: -0.0000

Data Index: 685494 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1035846 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9226. Min Act: -0.0000

Data Index: 979993 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1315107 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8324. Min Act: -0.0000

Data Index: 598947 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1490750 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8859. Min Act: -0.0000

Data Index: 573976 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8688. Min Act: -0.0000

Data Index: 62985 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8710. Min Act: -0.0000

Data Index: 241808 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8680. Min Act: -0.0000

Data Index: 263896 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1558380 (Python Code)

Max Activating Token Index: 933

Text #18

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.8095. Min Act: -0.0000

Data Index: 663798 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 1.1584. Min Range: -1.1584

Max Act: 0.9079. Min Act: -0.0000

Data Index: 25287 (C4 (Web Text))

Max Activating Token Index: 1015