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

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

Neuron 3839 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5646. Min Act: -0.0001

Data Index: 400606 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.6248. Min Act: -0.0001

Data Index: 510699 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.6621. Min Act: -0.0001

Data Index: 1252767 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.6046. Min Act: -0.0001

Data Index: 87575 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5605. Min Act: -0.0001

Data Index: 1103561 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5926. Min Act: -0.0001

Data Index: 435327 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.7629. Min Act: -0.0001

Data Index: 661747 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.4994. Min Act: -0.0001

Data Index: 287414 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.4768. Min Act: -0.0001

Data Index: 621179 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.4780. Min Act: -0.0001

Data Index: 1124672 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5690. Min Act: -0.0001

Data Index: 600726 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5243. Min Act: -0.0001

Data Index: 1205381 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.6635. Min Act: -0.0001

Data Index: 734032 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5903. Min Act: -0.0001

Data Index: 1201719 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5426. Min Act: -0.0001

Data Index: 160674 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5426. Min Act: -0.0001

Data Index: 591231 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5426. Min Act: -0.0001

Data Index: 1144193 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.4826. Min Act: -0.0001

Data Index: 917276 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.5203. Min Act: -0.0001

Data Index: 1297021 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 1.7629. Min Range: -1.7629

Max Act: 1.6259. Min Act: -0.0001

Data Index: 1242871 (C4 (Web Text))

Max Activating Token Index: 700