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

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

Neuron 1765 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: 3.4025. Min Range: -3.4025

Max Act: 3.4025. Min Act: -0.1698

Data Index: 1576423 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.3282. Min Act: -0.1700

Data Index: 1423989 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.2936. Min Act: -0.1697

Data Index: 1632761 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.3109. Min Act: -0.1696

Data Index: 1407056 (Python Code)

Max Activating Token Index: 252

Text #4

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.2909. Min Act: -0.1700

Data Index: 1412805 (Python Code)

Max Activating Token Index: 817

Text #5

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.2360. Min Act: -0.1699

Data Index: 1524570 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1599. Min Act: -0.1700

Data Index: 1471477 (Python Code)

Max Activating Token Index: 448

Text #7

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1477. Min Act: -0.1700

Data Index: 1600576 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1431. Min Act: -0.1700

Data Index: 1499448 (Python Code)

Max Activating Token Index: 232

Text #9

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1075. Min Act: -0.1687

Data Index: 1656362 (Python Code)

Max Activating Token Index: 33

Text #10

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1146. Min Act: -0.1700

Data Index: 1398679 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1060. Min Act: -0.1694

Data Index: 1385933 (Python Code)

Max Activating Token Index: 313

Text #12

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1014. Min Act: -0.1700

Data Index: 1623611 (Python Code)

Max Activating Token Index: 477

Text #13

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1031. Min Act: -0.1699

Data Index: 1455882 (Python Code)

Max Activating Token Index: 581

Text #14

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1120. Min Act: -0.1595

Data Index: 1372923 (Python Code)

Max Activating Token Index: 194

Text #15

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1362. Min Act: -0.1697

Data Index: 1446694 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1189. Min Act: -0.1700

Data Index: 1620415 (Python Code)

Max Activating Token Index: 613

Text #17

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1018. Min Act: -0.1695

Data Index: 1493378 (Python Code)

Max Activating Token Index: 971

Text #18

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.1015. Min Act: -0.1700

Data Index: 1599786 (Python Code)

Max Activating Token Index: 324

Text #19

Max Range: 3.4025. Min Range: -3.4025

Max Act: 3.0980. Min Act: -0.1700

Data Index: 1582433 (Python Code)

Max Activating Token Index: 1023