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

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

Neuron 1190 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: 4.3903. Min Range: -4.3903

Max Act: 4.3847. Min Act: -0.1696

Data Index: 1380918 (Python Code)

Max Activating Token Index: 172

Text #1

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.3903. Min Act: -0.1695

Data Index: 1556777 (Python Code)

Max Activating Token Index: 439

Text #2

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.3585. Min Act: -0.1695

Data Index: 1611918 (Python Code)

Max Activating Token Index: 776

Text #3

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.3220. Min Act: -0.1700

Data Index: 29217 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.3507. Min Act: -0.1700

Data Index: 1576676 (Python Code)

Max Activating Token Index: 560

Text #5

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.3035. Min Act: -0.1695

Data Index: 745233 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.3074. Min Act: -0.1695

Data Index: 1449172 (Python Code)

Max Activating Token Index: 1010

Text #7

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.2719. Min Act: -0.1698

Data Index: 1444499 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.2286. Min Act: -0.1695

Data Index: 1644902 (Python Code)

Max Activating Token Index: 736

Text #9

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.2153. Min Act: -0.1695

Data Index: 1487843 (Python Code)

Max Activating Token Index: 584

Text #10

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.2266. Min Act: -0.1695

Data Index: 179457 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.2102. Min Act: -0.1695

Data Index: 1481184 (Python Code)

Max Activating Token Index: 723

Text #12

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.1945. Min Act: -0.1695

Data Index: 1391742 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.1909. Min Act: -0.1695

Data Index: 1503543 (Python Code)

Max Activating Token Index: 598

Text #14

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.1766. Min Act: -0.1699

Data Index: 55873 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.1743. Min Act: -0.1700

Data Index: 724482 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.1442. Min Act: -0.1695

Data Index: 1578837 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.1434. Min Act: -0.1700

Data Index: 1585484 (Python Code)

Max Activating Token Index: 751

Text #18

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.1071. Min Act: -0.1700

Data Index: 1645836 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 4.3903. Min Range: -4.3903

Max Act: 4.1109. Min Act: -0.1697

Data Index: 1606838 (Python Code)

Max Activating Token Index: 385