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

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

Neuron 1751 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: 3.3837. Min Range: -3.3837

Max Act: 3.3837. Min Act: -0.1699

Data Index: 1358008 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.2314. Min Act: -0.1700

Data Index: 1330270 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.2091. Min Act: -0.1699

Data Index: 1141179 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.2090. Min Act: -0.1700

Data Index: 1187418 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.2216. Min Act: -0.1700

Data Index: 832309 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1736. Min Act: -0.1700

Data Index: 1330805 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1808. Min Act: -0.1700

Data Index: 552408 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1937. Min Act: -0.1699

Data Index: 1106823 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1414. Min Act: -0.1698

Data Index: 706287 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1354. Min Act: -0.1699

Data Index: 1319788 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1525. Min Act: -0.1700

Data Index: 1303479 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1589. Min Act: -0.1700

Data Index: 83700 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1440. Min Act: -0.1700

Data Index: 188081 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1004. Min Act: -0.1700

Data Index: 1245991 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1142. Min Act: -0.1699

Data Index: 1105711 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1224. Min Act: -0.1700

Data Index: 467585 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1159. Min Act: -0.1700

Data Index: 865032 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1067. Min Act: -0.1700

Data Index: 850094 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.1187. Min Act: -0.1696

Data Index: 1116353 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 3.3837. Min Range: -3.3837

Max Act: 3.0857. Min Act: -0.1700

Data Index: 105480 (C4 (Web Text))

Max Activating Token Index: 186