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

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

Neuron 1980 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0001

Data Index: 106611 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0476. Min Act: -0.0001

Data Index: 951477 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1026697 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0466. Min Act: -0.0001

Data Index: 1304733 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1329044 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0446. Min Act: -0.0001

Data Index: 339 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0391. Min Act: -0.0001

Data Index: 780733 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0439. Min Act: -0.0001

Data Index: 70751 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0439. Min Act: -0.0001

Data Index: 464548 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0405. Min Act: -0.0001

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1081916 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0436. Min Act: -0.0001

Data Index: 833497 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0391. Min Act: -0.0001

Data Index: 565885 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0407. Min Act: -0.0001

Data Index: 549866 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1307910 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0397. Min Act: -0.0001

Data Index: 1544698 (Python Code)

Max Activating Token Index: 324

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0439. Min Act: -0.0001

Data Index: 795544 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0415. Min Act: -0.0001

Data Index: 163466 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0412. Min Act: -0.0001

Data Index: 797262 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0393. Min Act: -0.0001

Data Index: 983855 (C4 (Web Text))

Max Activating Token Index: 921