Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2193 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7946. Min Act: -0.0001

Data Index: 720375 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6698. Min Act: -0.0001

Data Index: 1216087 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1354046 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5887. Min Act: -0.0001

Data Index: 1174642 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5898. Min Act: -0.0000

Data Index: 92381 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5842. Min Act: -0.0001

Data Index: 165056 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5838. Min Act: -0.0001

Data Index: 991686 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5768. Min Act: -0.0000

Data Index: 349584 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5570. Min Act: -0.0000

Data Index: 65227 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5715. Min Act: -0.0001

Data Index: 347276 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5734. Min Act: 0.0000

Data Index: 748706 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1005034 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5827. Min Act: -0.0000

Data Index: 111562 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5383. Min Act: -0.0000

Data Index: 19857 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5540. Min Act: -0.0000

Data Index: 968678 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5387. Min Act: -0.0000

Data Index: 98024 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5326. Min Act: -0.0001

Data Index: 564079 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5317. Min Act: 0.0000

Data Index: 50810 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5428. Min Act: -0.0000

Data Index: 473584 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1201638 (C4 (Web Text))

Max Activating Token Index: 682