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

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

Neuron 1921 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: 4.0274. Min Range: -4.0274

Max Act: 4.0274. Min Act: -0.1700

Data Index: 1613162 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7233. Min Act: -0.1699

Data Index: 192204 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.6694. Min Act: -0.1699

Data Index: 621968 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.6453. Min Act: -0.1698

Data Index: 1431605 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.6187. Min Act: -0.1692

Data Index: 1603201 (Python Code)

Max Activating Token Index: 400

Text #5

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.5695. Min Act: -0.1657

Data Index: 1437068 (Python Code)

Max Activating Token Index: 619

Text #6

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.5615. Min Act: -0.1700

Data Index: 1373238 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.5486. Min Act: -0.1700

Data Index: 1587625 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.5432. Min Act: -0.1696

Data Index: 1563514 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.4985. Min Act: -0.1698

Data Index: 283609 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.4808. Min Act: -0.1700

Data Index: 1609883 (Python Code)

Max Activating Token Index: 843

Text #11

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.4731. Min Act: -0.1700

Data Index: 1622883 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.4785. Min Act: -0.1700

Data Index: 414404 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.4394. Min Act: -0.1700

Data Index: 1448506 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.4222. Min Act: -0.1700

Data Index: 1633297 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.3975. Min Act: -0.1700

Data Index: 1477923 (Python Code)

Max Activating Token Index: 604

Text #16

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.3715. Min Act: -0.1700

Data Index: 1506724 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.3805. Min Act: -0.1699

Data Index: 305794 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.3711. Min Act: -0.1700

Data Index: 1558117 (Python Code)

Max Activating Token Index: 319

Text #19

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.3702. Min Act: -0.1700

Data Index: 1537846 (Python Code)

Max Activating Token Index: 1023