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

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

Neuron 1070 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0443. Min Act: -0.0002

Data Index: 250522 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1136244 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1160286 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0423. Min Act: -0.0003

Data Index: 531060 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0413. Min Act: -0.0003

Data Index: 753015 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0412. Min Act: -0.0002

Data Index: 391823 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0400. Min Act: -0.0002

Data Index: 232323 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0407. Min Act: -0.0003

Data Index: 932439 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0400. Min Act: -0.0002

Data Index: 127083 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1029172 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0400. Min Act: -0.0002

Data Index: 677941 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1117572 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0397. Min Act: -0.0002

Data Index: 146462 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1004808 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1063354 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1160470 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0389. Min Act: -0.0003

Data Index: 696602 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0380. Min Act: -0.0003

Data Index: 54291 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1626818 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.0443. Min Range: -0.0443

Max Act: 0.0377. Min Act: -0.0002

Data Index: 245262 (C4 (Web Text))

Max Activating Token Index: 5