Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 53 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1248925 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0641. Min Act: -0.0001

Data Index: 3969 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0627. Min Act: -0.0001

Data Index: 554586 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0681. Min Act: -0.0001

Data Index: 26299 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0649. Min Act: -0.0001

Data Index: 860638 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0589. Min Act: -0.0001

Data Index: 803086 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0648. Min Act: -0.0001

Data Index: 937035 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1302660 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0622. Min Act: -0.0001

Data Index: 292868 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1185956 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0573. Min Act: -0.0001

Data Index: 566369 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1232959 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0552. Min Act: -0.0001

Data Index: 73065 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0604. Min Act: -0.0001

Data Index: 624980 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0603. Min Act: -0.0001

Data Index: 528584 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0581. Min Act: -0.0001

Data Index: 734482 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1353706 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0625. Min Act: -0.0001

Data Index: 777900 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1262537 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0576. Min Act: -0.0001

Data Index: 477230 (C4 (Web Text))

Max Activating Token Index: 48