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

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

Neuron 1470 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1198318 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.2363. Min Act: -0.0000

Data Index: 634821 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.2324. Min Act: -0.0000

Data Index: 95028 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.1447. Min Act: -0.0000

Data Index: 641843 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.1839. Min Act: -0.0000

Data Index: 849768 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.1491. Min Act: -0.0000

Data Index: 760816 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.1708. Min Act: -0.0000

Data Index: 783447 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.0556. Min Act: -0.0000

Data Index: 829161 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.0974. Min Act: -0.0000

Data Index: 547056 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.0220. Min Act: -0.0000

Data Index: 662281 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.0521. Min Act: -0.0000

Data Index: 623523 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.0490. Min Act: -0.0000

Data Index: 472136 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.9916. Min Act: -0.0000

Data Index: 145915 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.0223. Min Act: -0.0000

Data Index: 918095 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.0226. Min Act: -0.0000

Data Index: 1101755 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.0402. Min Act: -0.0000

Data Index: 830300 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.9911. Min Act: -0.0000

Data Index: 701795 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.9991. Min Act: -0.0000

Data Index: 666388 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1232685 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.9663. Min Act: -0.0000

Data Index: 54560 (C4 (Web Text))

Max Activating Token Index: 889