Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1708 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.7525. Min Act: -0.1700

Data Index: 1575114 (Python Code)

Max Activating Token Index: 260

Text #1

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.7401. Min Act: -0.1700

Data Index: 190571 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.6814. Min Act: -0.1700

Data Index: 1491797 (Python Code)

Max Activating Token Index: 137

Text #3

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.6617. Min Act: -0.1700

Data Index: 1580415 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1333398 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5954. Min Act: -0.1700

Data Index: 1508514 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5719. Min Act: -0.1700

Data Index: 1461526 (Python Code)

Max Activating Token Index: 940

Text #7

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5765. Min Act: -0.1700

Data Index: 1176536 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5784. Min Act: -0.1700

Data Index: 1176371 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5778. Min Act: -0.1700

Data Index: 517053 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.6126. Min Act: -0.1700

Data Index: 347939 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5859. Min Act: -0.1700

Data Index: 1491575 (Python Code)

Max Activating Token Index: 536

Text #12

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5649. Min Act: -0.1700

Data Index: 1649642 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5290. Min Act: -0.1700

Data Index: 604011 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5800. Min Act: -0.1700

Data Index: 1526080 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5434. Min Act: -0.1700

Data Index: 485956 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5361. Min Act: -0.1700

Data Index: 1389061 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5494. Min Act: -0.1700

Data Index: 1390331 (Python Code)

Max Activating Token Index: 678

Text #18

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5422. Min Act: -0.1700

Data Index: 1412583 (Python Code)

Max Activating Token Index: 612

Text #19

Max Range: 3.7525. Min Range: -3.7525

Max Act: 3.5415. Min Act: -0.1700

Data Index: 862922 (C4 (Web Text))

Max Activating Token Index: 573