Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 20 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1798. Min Act: -0.0000

Data Index: 679726 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1639. Min Act: -0.0000

Data Index: 214296 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1049054 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1513. Min Act: -0.0000

Data Index: 66798 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1563. Min Act: -0.0000

Data Index: 888727 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1516155 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1177380 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1299951 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1316906 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1389. Min Act: -0.0000

Data Index: 409284 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1340. Min Act: -0.0000

Data Index: 258690 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1333. Min Act: -0.0000

Data Index: 104549 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1325. Min Act: -0.0000

Data Index: 81098 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1522638 (Python Code)

Max Activating Token Index: 1010

Text #14

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1263. Min Act: -0.0000

Data Index: 401536 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1397814 (Python Code)

Max Activating Token Index: 550

Text #16

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1642402 (Python Code)

Max Activating Token Index: 275

Text #17

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1260. Min Act: -0.0000

Data Index: 712635 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1491541 (Python Code)

Max Activating Token Index: 328

Text #19

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1246. Min Act: -0.0000

Data Index: 583827 (C4 (Web Text))

Max Activating Token Index: 881