Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1680 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.7516. Min Range: -8.7516

Max Act: 8.7516. Min Act: -0.1700

Data Index: 1397388 (Python Code)

Max Activating Token Index: 260

Text #1

Max Range: 8.7516. Min Range: -8.7516

Max Act: 8.2829. Min Act: -0.1700

Data Index: 1007763 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 8.7516. Min Range: -8.7516

Max Act: 8.1266. Min Act: -0.1700

Data Index: 1605687 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.8141. Min Act: -0.1700

Data Index: 1585400 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.7360. Min Act: -0.1700

Data Index: 1376362 (Python Code)

Max Activating Token Index: 1003

Text #5

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.6423. Min Act: -0.1700

Data Index: 776249 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.5485. Min Act: -0.1700

Data Index: 1629354 (Python Code)

Max Activating Token Index: 924

Text #7

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.5173. Min Act: -0.1700

Data Index: 1512051 (Python Code)

Max Activating Token Index: 522

Text #8

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.4860. Min Act: -0.1700

Data Index: 1480091 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.4704. Min Act: -0.1700

Data Index: 1440243 (Python Code)

Max Activating Token Index: 619

Text #10

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.4391. Min Act: -0.1700

Data Index: 1611487 (Python Code)

Max Activating Token Index: 256

Text #11

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.4235. Min Act: -0.1700

Data Index: 1656928 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.3298. Min Act: -0.1700

Data Index: 1498862 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.3766. Min Act: -0.1700

Data Index: 489564 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.3454. Min Act: -0.1700

Data Index: 1414810 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.3766. Min Act: -0.1700

Data Index: 1492569 (Python Code)

Max Activating Token Index: 919

Text #16

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.4235. Min Act: -0.1700

Data Index: 1382431 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.2829. Min Act: -0.1700

Data Index: 1456573 (Python Code)

Max Activating Token Index: 382

Text #18

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.3610. Min Act: -0.1700

Data Index: 1455434 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 8.7516. Min Range: -8.7516

Max Act: 7.2673. Min Act: -0.1700

Data Index: 1390985 (Python Code)

Max Activating Token Index: 457