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

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

Neuron 1206 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0001

Data Index: 102959 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0733. Min Act: -0.0001

Data Index: 631314 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1248241 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1036373 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0708. Min Act: -0.0001

Data Index: 638986 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0757. Min Act: -0.0001

Data Index: 775010 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0726. Min Act: -0.0001

Data Index: 856191 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0664. Min Act: -0.0001

Data Index: 622042 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0644. Min Act: -0.0001

Data Index: 92392 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0659. Min Act: -0.0001

Data Index: 369815 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0690. Min Act: -0.0001

Data Index: 45986 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0723. Min Act: -0.0001

Data Index: 929629 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0662. Min Act: -0.0001

Data Index: 407514 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0591. Min Act: -0.0001

Data Index: 123619 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0672. Min Act: -0.0001

Data Index: 207871 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1171161 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0680. Min Act: -0.0001

Data Index: 837638 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1250364 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0676. Min Act: -0.0001

Data Index: 4745 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1190257 (C4 (Web Text))

Max Activating Token Index: 96