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

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

Neuron 1513 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: 3.9642. Min Range: -3.9642

Max Act: 3.9642. Min Act: -0.1700

Data Index: 912383 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.9000. Min Act: -0.1700

Data Index: 466571 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.8884. Min Act: -0.1700

Data Index: 1338106 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.8599. Min Act: -0.1700

Data Index: 484096 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.8528. Min Act: -0.1700

Data Index: 1101463 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.8609. Min Act: -0.1700

Data Index: 1182828 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.8271. Min Act: -0.1700

Data Index: 533985 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.8311. Min Act: -0.1700

Data Index: 903404 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.8040. Min Act: -0.1700

Data Index: 16966 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.8018. Min Act: -0.1700

Data Index: 726616 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7999. Min Act: -0.1700

Data Index: 612395 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7744. Min Act: -0.1700

Data Index: 13755 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7740. Min Act: -0.1700

Data Index: 453748 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7832. Min Act: -0.1700

Data Index: 1092079 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7634. Min Act: -0.1700

Data Index: 1218534 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7600. Min Act: -0.1700

Data Index: 461966 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7652. Min Act: -0.1700

Data Index: 1334760 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7636. Min Act: -0.1700

Data Index: 204416 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7735. Min Act: -0.1700

Data Index: 283241 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 3.9642. Min Range: -3.9642

Max Act: 3.7411. Min Act: -0.1700

Data Index: 271133 (C4 (Web Text))

Max Activating Token Index: 224