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

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

Neuron 1802 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: 0.0013. Min Range: -0.0013

Max Act: 0.0013. Min Act: -0.0006

Data Index: 1270741 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0012. Min Act: -0.0006

Data Index: 721791 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0012. Min Act: -0.0006

Data Index: 1225275 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0012. Min Act: -0.0006

Data Index: 369058 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 172519 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 1014349 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 906949 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 342517 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 837707 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 1284436 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 195420 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0007

Data Index: 11883 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 496313 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0005

Data Index: 286237 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 496123 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0006

Data Index: 519434 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0006

Data Index: 929112 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 1322405 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0011. Min Act: -0.0006

Data Index: 1102171 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.0013. Min Range: -0.0013

Max Act: 0.0010. Min Act: -0.0006

Data Index: 435182 (C4 (Web Text))

Max Activating Token Index: 473