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

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

Neuron 517 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: 3.8790. Min Range: -3.8790

Max Act: 3.8790. Min Act: -0.1698

Data Index: 1528909 (Python Code)

Max Activating Token Index: 498

Text #1

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.8012. Min Act: -0.1700

Data Index: 1204668 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.7062. Min Act: -0.1699

Data Index: 1607980 (Python Code)

Max Activating Token Index: 493

Text #3

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.7147. Min Act: -0.1526

Data Index: 1511894 (Python Code)

Max Activating Token Index: 495

Text #4

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.7005. Min Act: -0.1526

Data Index: 1420984 (Python Code)

Max Activating Token Index: 886

Text #5

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.6410. Min Act: -0.1526

Data Index: 1553643 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5805. Min Act: -0.1685

Data Index: 575364 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.6038. Min Act: -0.1699

Data Index: 1631677 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5849. Min Act: -0.1700

Data Index: 394066 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5992. Min Act: -0.1700

Data Index: 800028 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5548. Min Act: -0.1689

Data Index: 1393405 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5492. Min Act: -0.1700

Data Index: 1386910 (Python Code)

Max Activating Token Index: 485

Text #12

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5612. Min Act: -0.1700

Data Index: 934141 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5505. Min Act: -0.1651

Data Index: 805843 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5529. Min Act: -0.1700

Data Index: 903663 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5368. Min Act: -0.1694

Data Index: 1437571 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.5393. Min Act: -0.1688

Data Index: 1631569 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.4989. Min Act: -0.1699

Data Index: 407787 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.4942. Min Act: -0.1699

Data Index: 993806 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 3.8790. Min Range: -3.8790

Max Act: 3.4975. Min Act: -0.1700

Data Index: 1488216 (Python Code)

Max Activating Token Index: 540