Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 252 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1131709 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4567. Min Act: -0.0000

Data Index: 715360 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1080211 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4109. Min Act: -0.0000

Data Index: 552007 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4129. Min Act: 0.0000

Data Index: 446516 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3815. Min Act: -0.0000

Data Index: 563445 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3800. Min Act: -0.0000

Data Index: 366286 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3806. Min Act: -0.0001

Data Index: 691166 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3808. Min Act: 0.0000

Data Index: 706050 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1060464 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3752. Min Act: -0.0000

Data Index: 565493 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3738. Min Act: 0.0001

Data Index: 730372 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3712. Min Act: -0.0000

Data Index: 938924 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3717. Min Act: -0.0001

Data Index: 995818 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3834. Min Act: -0.0000

Data Index: 388305 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3800. Min Act: 0.0001

Data Index: 482782 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3342. Min Act: -0.0000

Data Index: 441112 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3640. Min Act: 0.0001

Data Index: 257946 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3493. Min Act: -0.0000

Data Index: 357702 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.3621. Min Act: 0.0000

Data Index: 1217236 (C4 (Web Text))

Max Activating Token Index: 383