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

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

Neuron 4136 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.5509. Min Act: -0.0000

Data Index: 657617 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 3.5509. Min Range: -3.5509

Max Act: 3.0580. Min Act: -0.0000

Data Index: 769864 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.7400. Min Act: -0.0000

Data Index: 999236 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.5721. Min Act: -0.0000

Data Index: 370078 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.5394. Min Act: -0.0000

Data Index: 30877 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.3543. Min Act: -0.0000

Data Index: 107918 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.5145. Min Act: -0.0000

Data Index: 1070357 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.4698. Min Act: -0.0000

Data Index: 301963 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.3078. Min Act: -0.0000

Data Index: 235485 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.0689. Min Act: -0.0000

Data Index: 1481650 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.2631. Min Act: -0.0000

Data Index: 1266524 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.3511. Min Act: -0.0000

Data Index: 501502 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.0688. Min Act: -0.0000

Data Index: 263231 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.0984. Min Act: -0.0000

Data Index: 451293 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.1012. Min Act: -0.0000

Data Index: 695520 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.3003. Min Act: -0.0000

Data Index: 1279691 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.0751. Min Act: -0.0000

Data Index: 78297 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.0404. Min Act: -0.0000

Data Index: 206085 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.2644. Min Act: -0.0000

Data Index: 1114371 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 3.5509. Min Range: -3.5509

Max Act: 2.0141. Min Act: -0.0000

Data Index: 1279742 (C4 (Web Text))

Max Activating Token Index: 737