Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 804 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0015. Min Act: -0.0006

Data Index: 1007882 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0013. Min Act: -0.0006

Data Index: 951562 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0005

Data Index: 1472981 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0006

Data Index: 294184 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0006

Data Index: 661986 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0012. Min Act: -0.0006

Data Index: 57041 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0011. Min Act: -0.0006

Data Index: 1158544 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0011. Min Act: -0.0006

Data Index: 606149 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0011. Min Act: -0.0006

Data Index: 452851 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0011. Min Act: -0.0007

Data Index: 634741 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0011. Min Act: -0.0006

Data Index: 564170 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0010. Min Act: -0.0006

Data Index: 556002 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0011. Min Act: -0.0006

Data Index: 955934 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0010. Min Act: -0.0006

Data Index: 1242451 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0010. Min Act: -0.0006

Data Index: 991515 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0011. Min Act: -0.0006

Data Index: 646861 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0010. Min Act: -0.0006

Data Index: 1358095 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0010. Min Act: -0.0006

Data Index: 458183 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0010. Min Act: -0.0006

Data Index: 1109927 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0010. Min Act: -0.0006

Data Index: 162823 (C4 (Web Text))

Max Activating Token Index: 309