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

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

Neuron 680 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3650. Min Range: -4.3650

Max Act: 4.3650. Min Act: -0.1700

Data Index: 1583828 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 4.3650. Min Range: -4.3650

Max Act: 4.1774. Min Act: -0.1700

Data Index: 1625786 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.8022. Min Act: -0.1700

Data Index: 1621656 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.7709. Min Act: -0.1700

Data Index: 1498970 (Python Code)

Max Activating Token Index: 534

Text #4

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.8022. Min Act: -0.1700

Data Index: 1608936 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.7396. Min Act: -0.1700

Data Index: 1589368 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.7084. Min Act: -0.1700

Data Index: 1533255 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6771. Min Act: -0.1700

Data Index: 1521598 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6771. Min Act: -0.1700

Data Index: 1440844 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6458. Min Act: -0.1700

Data Index: 1433412 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6771. Min Act: -0.1700

Data Index: 1413592 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6771. Min Act: -0.1700

Data Index: 1464533 (Python Code)

Max Activating Token Index: 924

Text #12

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6144. Min Act: -0.1700

Data Index: 1367671 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6771. Min Act: -0.1700

Data Index: 1634730 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6771. Min Act: -0.1700

Data Index: 1619705 (Python Code)

Max Activating Token Index: 554

Text #15

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6144. Min Act: -0.1700

Data Index: 1582510 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.5831. Min Act: -0.1700

Data Index: 1595372 (Python Code)

Max Activating Token Index: 593

Text #17

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6144. Min Act: -0.1700

Data Index: 1397408 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.6144. Min Act: -0.1700

Data Index: 1522920 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 4.3650. Min Range: -4.3650

Max Act: 3.5831. Min Act: -0.1700

Data Index: 1471392 (Python Code)

Max Activating Token Index: 30