Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1496 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1613869 (Python Code)

Max Activating Token Index: 584

Text #1

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1609312 (Python Code)

Max Activating Token Index: 584

Text #2

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1616. Min Act: -0.0002

Data Index: 1459512 (Python Code)

Max Activating Token Index: 517

Text #3

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1415592 (Python Code)

Max Activating Token Index: 756

Text #4

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1571. Min Act: -0.0002

Data Index: 1411533 (Python Code)

Max Activating Token Index: 355

Text #5

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1536308 (Python Code)

Max Activating Token Index: 234

Text #6

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1432747 (Python Code)

Max Activating Token Index: 598

Text #7

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1653. Min Act: -0.0002

Data Index: 1620264 (Python Code)

Max Activating Token Index: 407

Text #8

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1572. Min Act: -0.0002

Data Index: 1649276 (Python Code)

Max Activating Token Index: 906

Text #9

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1598. Min Act: -0.0002

Data Index: 1562944 (Python Code)

Max Activating Token Index: 685

Text #10

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1538820 (Python Code)

Max Activating Token Index: 449

Text #11

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1531. Min Act: -0.0002

Data Index: 1429415 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1502. Min Act: -0.0002

Data Index: 1386554 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1620195 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1487602 (Python Code)

Max Activating Token Index: 956

Text #15

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1618641 (Python Code)

Max Activating Token Index: 935

Text #16

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1474. Min Act: -0.0002

Data Index: 1453485 (Python Code)

Max Activating Token Index: 692

Text #17

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1524. Min Act: -0.0002

Data Index: 1505571 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1473. Min Act: -0.0002

Data Index: 1557765 (Python Code)

Max Activating Token Index: 1002

Text #19

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1380088 (Python Code)

Max Activating Token Index: 201