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

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

Neuron 557 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: 3.4849. Min Range: -3.4849

Max Act: 3.4849. Min Act: -0.1700

Data Index: 906480 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.2204. Min Act: -0.1700

Data Index: 354766 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1851. Min Act: -0.1700

Data Index: 74848 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1818. Min Act: -0.1699

Data Index: 628324 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1770. Min Act: -0.1693

Data Index: 431931 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1782. Min Act: -0.1684

Data Index: 565359 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1719. Min Act: -0.1700

Data Index: 342035 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1491. Min Act: -0.1684

Data Index: 621322 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1357. Min Act: -0.1699

Data Index: 1141226 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1447. Min Act: -0.1684

Data Index: 131958 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1517. Min Act: -0.1697

Data Index: 1007423 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1161. Min Act: -0.1684

Data Index: 712209 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1157. Min Act: -0.1692

Data Index: 645206 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1199. Min Act: -0.1700

Data Index: 951779 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1117. Min Act: -0.1700

Data Index: 475503 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1333. Min Act: -0.1696

Data Index: 115838 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1185. Min Act: -0.1698

Data Index: 729082 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.0967. Min Act: -0.1700

Data Index: 479454 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1003. Min Act: -0.1684

Data Index: 1005381 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.0809. Min Act: -0.1695

Data Index: 742672 (C4 (Web Text))

Max Activating Token Index: 859