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

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

Neuron 794 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: 3.2707. Min Range: -3.2707

Max Act: 3.2707. Min Act: -0.1698

Data Index: 1372371 (Python Code)

Max Activating Token Index: 648

Text #1

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.2350. Min Act: -0.1662

Data Index: 1621220 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.1437. Min Act: -0.1662

Data Index: 1605411 (Python Code)

Max Activating Token Index: 444

Text #3

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.1252. Min Act: -0.1700

Data Index: 1541315 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.0910. Min Act: -0.1699

Data Index: 770982 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.0135. Min Act: -0.1694

Data Index: 1490881 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.0208. Min Act: -0.1698

Data Index: 1569320 (Python Code)

Max Activating Token Index: 599

Text #7

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.0030. Min Act: -0.1662

Data Index: 1432058 (Python Code)

Max Activating Token Index: 904

Text #8

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9812. Min Act: -0.1662

Data Index: 1623033 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9728. Min Act: -0.1700

Data Index: 1399343 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9800. Min Act: -0.1662

Data Index: 1486314 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9546. Min Act: -0.1700

Data Index: 1589160 (Python Code)

Max Activating Token Index: 643

Text #12

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9255. Min Act: -0.1696

Data Index: 309379 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9133. Min Act: -0.1700

Data Index: 1421356 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9190. Min Act: -0.1662

Data Index: 1365658 (Python Code)

Max Activating Token Index: 887

Text #15

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9220. Min Act: -0.1662

Data Index: 1482917 (Python Code)

Max Activating Token Index: 460

Text #16

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9196. Min Act: -0.1700

Data Index: 746190 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.8934. Min Act: -0.1662

Data Index: 1419551 (Python Code)

Max Activating Token Index: 548

Text #18

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9063. Min Act: -0.1662

Data Index: 1383099 (Python Code)

Max Activating Token Index: 145

Text #19

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9024. Min Act: -0.1662

Data Index: 1644144 (Python Code)

Max Activating Token Index: 319