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

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

Neuron 789 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: 3.4836. Min Range: -3.4836

Max Act: 3.4836. Min Act: -0.1700

Data Index: 1275117 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.3833. Min Act: -0.1700

Data Index: 699769 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1937. Min Act: -0.1700

Data Index: 973779 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1883. Min Act: -0.1700

Data Index: 1007138 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1941. Min Act: -0.1700

Data Index: 1028978 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1912. Min Act: -0.1700

Data Index: 195594 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1765. Min Act: -0.1700

Data Index: 101279 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1610. Min Act: -0.1700

Data Index: 243122 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1690. Min Act: -0.1700

Data Index: 1300085 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1629. Min Act: -0.1700

Data Index: 243197 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1480. Min Act: -0.1700

Data Index: 302338 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1309. Min Act: -0.1700

Data Index: 617355 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1217. Min Act: -0.1700

Data Index: 1316462 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1357. Min Act: -0.1700

Data Index: 1037551 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1449. Min Act: -0.1700

Data Index: 1101709 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1505. Min Act: -0.1700

Data Index: 963017 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1389. Min Act: -0.1700

Data Index: 972594 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1200. Min Act: -0.1700

Data Index: 1251486 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1419. Min Act: -0.1700

Data Index: 202428 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 3.4836. Min Range: -3.4836

Max Act: 3.1387. Min Act: -0.1700

Data Index: 726782 (C4 (Web Text))

Max Activating Token Index: 619