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

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

Neuron 4839 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: 0.1512. Min Range: -0.1512

Max Act: 0.1479. Min Act: -0.0002

Data Index: 1600742 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1512. Min Act: -0.0002

Data Index: 1406870 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1469. Min Act: -0.0002

Data Index: 1405950 (Python Code)

Max Activating Token Index: 910

Text #3

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1432. Min Act: -0.0002

Data Index: 1397548 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1440. Min Act: -0.0002

Data Index: 1417606 (Python Code)

Max Activating Token Index: 935

Text #5

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1430. Min Act: -0.0002

Data Index: 1383739 (Python Code)

Max Activating Token Index: 121

Text #6

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1547622 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1418. Min Act: -0.0002

Data Index: 1386355 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1417. Min Act: -0.0002

Data Index: 1525356 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1409. Min Act: -0.0002

Data Index: 1636764 (Python Code)

Max Activating Token Index: 959

Text #10

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1421. Min Act: -0.0002

Data Index: 1493582 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1394. Min Act: -0.0002

Data Index: 1506179 (Python Code)

Max Activating Token Index: 893

Text #12

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1427. Min Act: -0.0002

Data Index: 1625025 (Python Code)

Max Activating Token Index: 879

Text #13

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1374. Min Act: -0.0002

Data Index: 1549437 (Python Code)

Max Activating Token Index: 242

Text #14

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1428. Min Act: -0.0002

Data Index: 1572598 (Python Code)

Max Activating Token Index: 803

Text #15

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1634658 (Python Code)

Max Activating Token Index: 750

Text #16

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1381. Min Act: -0.0002

Data Index: 1414223 (Python Code)

Max Activating Token Index: 108

Text #17

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1372. Min Act: -0.0002

Data Index: 1647410 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1383. Min Act: -0.0002

Data Index: 1534071 (Python Code)

Max Activating Token Index: 914

Text #19

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1370. Min Act: -0.0002

Data Index: 1487203 (Python Code)

Max Activating Token Index: 956