Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 608 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0002

Data Index: 112898 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0442. Min Act: -0.0002

Data Index: 849792 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0424. Min Act: -0.0002

Data Index: 318630 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0426. Min Act: -0.0002

Data Index: 634883 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1128052 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0425. Min Act: -0.0002

Data Index: 569577 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1300136 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1279983 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0427. Min Act: -0.0002

Data Index: 523299 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0406. Min Act: -0.0002

Data Index: 946465 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1153695 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0412. Min Act: -0.0002

Data Index: 840603 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0403. Min Act: -0.0002

Data Index: 594970 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0418. Min Act: -0.0002

Data Index: 146497 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0400. Min Act: -0.0002

Data Index: 913170 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0420. Min Act: -0.0002

Data Index: 981181 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1464366 (Python Code)

Max Activating Token Index: 503

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0364. Min Act: -0.0002

Data Index: 405711 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0390. Min Act: -0.0002

Data Index: 226630 (C4 (Web Text))

Max Activating Token Index: 40