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

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

Neuron 1635 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: 4.2678. Min Range: -4.2678

Max Act: 4.2678. Min Act: -0.1219

Data Index: 1365657 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.2134. Min Act: -0.1700

Data Index: 388200 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1894. Min Act: -0.1227

Data Index: 1396564 (Python Code)

Max Activating Token Index: 504

Text #3

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.2157. Min Act: -0.1699

Data Index: 941720 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1979. Min Act: -0.1700

Data Index: 415049 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.2175. Min Act: -0.1367

Data Index: 449739 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1944. Min Act: -0.1479

Data Index: 1231326 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1695. Min Act: -0.1688

Data Index: 1067851 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1586. Min Act: -0.1698

Data Index: 1591423 (Python Code)

Max Activating Token Index: 476

Text #9

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1888. Min Act: -0.1678

Data Index: 1584013 (Python Code)

Max Activating Token Index: 169

Text #10

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1853. Min Act: -0.1700

Data Index: 1088883 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1684. Min Act: -0.1700

Data Index: 224771 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1318. Min Act: -0.1700

Data Index: 1385879 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1329. Min Act: -0.1700

Data Index: 1530009 (Python Code)

Max Activating Token Index: 582

Text #14

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1513. Min Act: -0.1688

Data Index: 1443605 (Python Code)

Max Activating Token Index: 962

Text #15

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1281. Min Act: -0.1699

Data Index: 1644653 (Python Code)

Max Activating Token Index: 662

Text #16

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1307. Min Act: -0.1697

Data Index: 1541252 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1555. Min Act: -0.1312

Data Index: 555969 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.0988. Min Act: -0.1597

Data Index: 1567617 (Python Code)

Max Activating Token Index: 824

Text #19

Max Range: 4.2678. Min Range: -4.2678

Max Act: 4.1305. Min Act: -0.1700

Data Index: 263556 (C4 (Web Text))

Max Activating Token Index: 850