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

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

Neuron 4319 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1495623 (Python Code)

Max Activating Token Index: 502

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1406970 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1583867 (Python Code)

Max Activating Token Index: 89

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1379257 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1372631 (Python Code)

Max Activating Token Index: 279

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1473873 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1416298 (Python Code)

Max Activating Token Index: 204

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1412864 (Python Code)

Max Activating Token Index: 750

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1650991 (Python Code)

Max Activating Token Index: 203

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1462172 (Python Code)

Max Activating Token Index: 249

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1369728 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1439946 (Python Code)

Max Activating Token Index: 895

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1627719 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1405265 (Python Code)

Max Activating Token Index: 374

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1446383 (Python Code)

Max Activating Token Index: 137

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1408024 (Python Code)

Max Activating Token Index: 453

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1461393 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1504309 (Python Code)

Max Activating Token Index: 833

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1424747 (Python Code)

Max Activating Token Index: 118

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1562306 (Python Code)

Max Activating Token Index: 226