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

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

Neuron 1316 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2504. Min Act: -0.0001

Data Index: 1563876 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2910. Min Act: -0.0001

Data Index: 1614897 (Python Code)

Max Activating Token Index: 539

Text #2

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1546050 (Python Code)

Max Activating Token Index: 363

Text #3

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2514. Min Act: -0.0001

Data Index: 1599866 (Python Code)

Max Activating Token Index: 535

Text #4

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2515. Min Act: -0.0001

Data Index: 1456777 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2387. Min Act: -0.0001

Data Index: 1479228 (Python Code)

Max Activating Token Index: 149

Text #6

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2386. Min Act: -0.0001

Data Index: 1570170 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2432. Min Act: -0.0001

Data Index: 1410948 (Python Code)

Max Activating Token Index: 290

Text #8

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1371538 (Python Code)

Max Activating Token Index: 353

Text #9

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1402387 (Python Code)

Max Activating Token Index: 388

Text #10

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1557016 (Python Code)

Max Activating Token Index: 305

Text #11

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2501. Min Act: -0.0001

Data Index: 1538436 (Python Code)

Max Activating Token Index: 446

Text #12

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2391. Min Act: -0.0001

Data Index: 1430461 (Python Code)

Max Activating Token Index: 431

Text #13

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1562717 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2283. Min Act: -0.0001

Data Index: 1575656 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1608405 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2375. Min Act: -0.0001

Data Index: 1604077 (Python Code)

Max Activating Token Index: 183

Text #17

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2354. Min Act: -0.0001

Data Index: 1370502 (Python Code)

Max Activating Token Index: 179

Text #18

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1614658 (Python Code)

Max Activating Token Index: 220

Text #19

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1619142 (Python Code)

Max Activating Token Index: 36