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

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

Neuron 538 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: 3.3736. Min Range: -3.3736

Max Act: 3.3736. Min Act: -0.1700

Data Index: 1505333 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.3145. Min Act: -0.1700

Data Index: 959821 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.2678. Min Act: -0.1700

Data Index: 1587090 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.2629. Min Act: -0.1700

Data Index: 116862 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.2253. Min Act: -0.1700

Data Index: 493047 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.2297. Min Act: -0.1700

Data Index: 1381434 (Python Code)

Max Activating Token Index: 386

Text #6

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.2422. Min Act: -0.1700

Data Index: 709427 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.2208. Min Act: -0.1700

Data Index: 637526 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.2067. Min Act: -0.1700

Data Index: 1011101 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.2068. Min Act: -0.1700

Data Index: 1064342 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1997. Min Act: -0.1700

Data Index: 1039575 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1784. Min Act: -0.1700

Data Index: 481356 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1599. Min Act: -0.1700

Data Index: 360794 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1868. Min Act: -0.1700

Data Index: 149733 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1729. Min Act: -0.1700

Data Index: 1257319 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1828. Min Act: -0.1700

Data Index: 748018 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1955. Min Act: -0.1700

Data Index: 540726 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1850. Min Act: -0.1700

Data Index: 649330 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1617. Min Act: -0.1700

Data Index: 139495 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 3.3736. Min Range: -3.3736

Max Act: 3.1661. Min Act: -0.1700

Data Index: 704498 (C4 (Web Text))

Max Activating Token Index: 636