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

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

Neuron 2633 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: 2.2512. Min Range: -2.2512

Max Act: 2.2512. Min Act: -0.0000

Data Index: 1058636 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 2.2512. Min Range: -2.2512

Max Act: 2.0822. Min Act: -0.0000

Data Index: 1348865 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.8602. Min Act: -0.0000

Data Index: 601670 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 2.2512. Min Range: -2.2512

Max Act: 2.0636. Min Act: -0.0000

Data Index: 1102376 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.9411. Min Act: -0.0000

Data Index: 1266635 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.9038. Min Act: -0.0000

Data Index: 558182 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.7917. Min Act: -0.0000

Data Index: 883174 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 2.2512. Min Range: -2.2512

Max Act: 2.1811. Min Act: -0.0000

Data Index: 229162 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.7761. Min Act: -0.0000

Data Index: 374676 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.6243. Min Act: -0.0000

Data Index: 38310 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.4994. Min Act: -0.0000

Data Index: 1212703 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.3743. Min Act: -0.0000

Data Index: 53389 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.1867. Min Act: -0.0000

Data Index: 343539 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.2915. Min Act: -0.0000

Data Index: 309845 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.2915. Min Act: -0.0000

Data Index: 723432 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.3668. Min Act: -0.0000

Data Index: 404778 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1314659 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.2338. Min Act: -0.0000

Data Index: 282692 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.2338. Min Act: -0.0000

Data Index: 834130 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 2.2512. Min Range: -2.2512

Max Act: 1.2310. Min Act: -0.0000

Data Index: 961631 (C4 (Web Text))

Max Activating Token Index: 351