Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5009 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.6070. Min Act: -0.0000

Data Index: 1531475 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.6484. Min Act: -0.0000

Data Index: 1523381 (Python Code)

Max Activating Token Index: 350

Text #2

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.5794. Min Act: -0.0000

Data Index: 1625050 (Python Code)

Max Activating Token Index: 538

Text #3

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.5396. Min Act: -0.0000

Data Index: 1444374 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.6032. Min Act: -0.0000

Data Index: 97770 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1008808 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.3963. Min Act: -0.0000

Data Index: 241822 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.3851. Min Act: -0.0000

Data Index: 353930 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.3834. Min Act: -0.0000

Data Index: 1430224 (Python Code)

Max Activating Token Index: 152

Text #9

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.3716. Min Act: -0.0000

Data Index: 386218 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.3755. Min Act: -0.0000

Data Index: 649037 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.4383. Min Act: -0.0000

Data Index: 902266 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1605683 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.2651. Min Act: -0.0000

Data Index: 509319 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.4245. Min Act: -0.0000

Data Index: 483309 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1449972 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.4674. Min Act: -0.0000

Data Index: 1601684 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.4654. Min Act: -0.0000

Data Index: 1642764 (Python Code)

Max Activating Token Index: 724

Text #18

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.3814. Min Act: -0.0000

Data Index: 275767 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.6484. Min Range: -1.6484

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1641743 (Python Code)

Max Activating Token Index: 1004