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

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

Neuron 5668 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2050. Min Range: -2.2050

Max Act: 2.1562. Min Act: -0.0000

Data Index: 1605082 (Python Code)

Max Activating Token Index: 559

Text #1

Max Range: 2.2050. Min Range: -2.2050

Max Act: 2.2050. Min Act: -0.0000

Data Index: 1400254 (Python Code)

Max Activating Token Index: 49

Text #2

Max Range: 2.2050. Min Range: -2.2050

Max Act: 2.1513. Min Act: -0.0001

Data Index: 1485033 (Python Code)

Max Activating Token Index: 95

Text #3

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.8902. Min Act: -0.0000

Data Index: 1392774 (Python Code)

Max Activating Token Index: 154

Text #4

Max Range: 2.2050. Min Range: -2.2050

Max Act: 2.0895. Min Act: -0.0001

Data Index: 1589359 (Python Code)

Max Activating Token Index: 103

Text #5

Max Range: 2.2050. Min Range: -2.2050

Max Act: 2.0810. Min Act: -0.0000

Data Index: 1464554 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 2.2050. Min Range: -2.2050

Max Act: 2.1346. Min Act: -0.0000

Data Index: 1598620 (Python Code)

Max Activating Token Index: 666

Text #7

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.9759. Min Act: -0.0000

Data Index: 1641822 (Python Code)

Max Activating Token Index: 56

Text #8

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.9547. Min Act: -0.0000

Data Index: 1385905 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.8022. Min Act: -0.0000

Data Index: 1559300 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.9647. Min Act: -0.0000

Data Index: 1361560 (Python Code)

Max Activating Token Index: 860

Text #11

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.8809. Min Act: -0.0000

Data Index: 1546687 (Python Code)

Max Activating Token Index: 31

Text #12

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.8598. Min Act: -0.0000

Data Index: 1455561 (Python Code)

Max Activating Token Index: 299

Text #13

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.8375. Min Act: -0.0000

Data Index: 1561684 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.7534. Min Act: -0.0000

Data Index: 1599429 (Python Code)

Max Activating Token Index: 845

Text #15

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.8836. Min Act: -0.0000

Data Index: 1582867 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.8679. Min Act: -0.0000

Data Index: 1559726 (Python Code)

Max Activating Token Index: 368

Text #17

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.8427. Min Act: -0.0000

Data Index: 1520807 (Python Code)

Max Activating Token Index: 381

Text #18

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.8591. Min Act: -0.0000

Data Index: 1602281 (Python Code)

Max Activating Token Index: 480

Text #19

Max Range: 2.2050. Min Range: -2.2050

Max Act: 1.7438. Min Act: -0.0000

Data Index: 1495186 (Python Code)

Max Activating Token Index: 620