Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1760 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.5065. Min Act: -0.1700

Data Index: 250044 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.1002. Min Act: -0.1700

Data Index: 791990 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.2252. Min Act: -0.1700

Data Index: 250222 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.1315. Min Act: -0.1700

Data Index: 535529 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.1315. Min Act: -0.1700

Data Index: 21478 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.2565. Min Act: -0.1700

Data Index: 1150380 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.2565. Min Act: -0.1700

Data Index: 1283479 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.1627. Min Act: -0.1700

Data Index: 865077 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.1627. Min Act: -0.1700

Data Index: 1265705 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.1315. Min Act: -0.1700

Data Index: 292979 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.0690. Min Act: -0.1700

Data Index: 1287248 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.1627. Min Act: -0.1700

Data Index: 152443 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.1002. Min Act: -0.1700

Data Index: 637597 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.0377. Min Act: -0.1699

Data Index: 1333131 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.0690. Min Act: -0.1700

Data Index: 280602 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.0377. Min Act: -0.1700

Data Index: 768268 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.0065. Min Act: -0.1700

Data Index: 372173 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.0065. Min Act: -0.1700

Data Index: 199938 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.0065. Min Act: -0.1700

Data Index: 742262 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 5.5065. Min Range: -5.5065

Max Act: 5.0377. Min Act: -0.1700

Data Index: 1107501 (C4 (Web Text))

Max Activating Token Index: 893