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

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

Neuron 325 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.3440. Min Act: -0.0001

Data Index: 75600 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.3342. Min Act: -0.0000

Data Index: 633783 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.1245. Min Act: -0.0000

Data Index: 901796 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1048999 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0949. Min Act: -0.0000

Data Index: 670071 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1152198 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1332521 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0861. Min Act: -0.0000

Data Index: 555699 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.1047. Min Act: -0.0000

Data Index: 1160889 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0077. Min Act: -0.0000

Data Index: 956416 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0026. Min Act: -0.0000

Data Index: 99341 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.3440. Min Range: -1.3440

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1012120 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0205. Min Act: -0.0000

Data Index: 880994 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0282. Min Act: -0.0000

Data Index: 803817 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0439. Min Act: -0.0000

Data Index: 333667 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1064423 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1111932 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1011225 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.3440. Min Range: -1.3440

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1168656 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 1.3440. Min Range: -1.3440

Max Act: 0.9646. Min Act: -0.0000

Data Index: 129663 (C4 (Web Text))

Max Activating Token Index: 744